Hōkū, by Deep3 Labs, analyzes each wallet's transaction history with advanced AI models and monitors network activity in real-time, so that we can deliver personalized token and dapp recommendations uniquely to each user with the speed of today's crypto markets, while our 3D network explorer reveals patterns that even the most advanced block explorers can't show.
Learn more about Hōkū [here](#hoku).
Accretion, by Deep3 Labs, is the industry’s first AI-powered, no-code digital marketing platform. Inspired by Google Ads, built by former Googlers. Using machine learning, Accretion allows you to target addresses most likely to convert and ensures your campaigns only get more profitable over time.
Learn more about Accretion [here](#accretion).
Exos, by Deep3 Labs, redefines blockchain security, shifting the focus from reactive to predictive protection. This no-code, AI-powered platform effortlessly identifies risky addresses and analyzes bot networks with pioneering 3D visuals. Guard against critical threats like unexpected token actions or contract alterations to ensure you’re always one step ahead.
Learn more about Exos [here](#exos).
that launches context-specific help docs directly in the interface. If you get stuck, this is the best first step.
But, for any other questions, or just to share feedback, reach out to us via one of our [community platforms](/community) or send us an email at 
that launches context-specific help docs directly in the interface. If you get stuck, this is the best first step.
But, for any other questions, or just to share feedback, reach out to us via one of our [community platforms](/community) or send us an email at 
.jpg?alt=media&token=83277692-d693-4a95-a331-427ff9b20d1e)
.jpg?alt=media&token=bb7a865e-ed30-480e-aab8-d229d78a7982)
symbol shown on the far left of the cluster title bar. To hide a cluster, simply click the 
symbol shown on the far right of the cluster title bar.
, which marks tokens that are *new or not recently seen* on that network. These are tokens that have just started drawing interest from that group of traders, often signaling early momentum or discovery before the wider market reacts. In most cases, they're newly launched tokens but in very rare cases if existing token hasn't been transferred or swapped for a very long time, it will also receive this badge.
to the right of the trading cluster title.
badge?
on the far right of each row.
. Any wallets you mark will appear on your favorites dashboard.
, Ethereum 
, or BNB Smart Chain 
).
* **Type:** whether the system is predicting a **Buy** 
or **Sell** 
momentum shift.
* **Strength:** the confidence level of the prediction (Low 
, Medium 
, or High 
).
* **Price Target:** the model’s projected directional change for the selected prediction window (for example, “+50%” or “–5%”). The price thresholds predicted vary for low and high liquidity tokens.
* **Token:** the token that triggered the signal.
* **For (Clusters)**: the specific trading clusters driving the signal. These indicate which groups of wallets are responsible for the underlying behavioral momentum.
* **First Seen:** when the system first detected this signal.
Because signals are behavior-based, they do not expire on a fixed schedule. Instead, they remain listed here until the underlying momentum dissipates, that is, when a token’s activity falls below the two-cluster threshold.
### Recent alerts
The **Recent Alerts** section displays trade signals that were **active within the past two hours** but are no longer meeting the criteria for ongoing momentum.
In other words, these are alerts that *recently* lost traction — tokens that were trending across multiple clusters but have since cooled off or consolidated.
, price decrease 
or that price change not predicted to be met 
.
Here are several examples of a single cell from the predictions table and the correct interpretation for each one:
High Confidence (86%) that a 20% price increase will occur in the next 1 hour
Low Confidence (31%) that a 5% price change will NOT occur in the next 1 hour
Low Confidence (15%) that a 5% price decrease will occur in the next 1 hour
1st row, 1st col: High confidence (79%) that a 5% price increase will NOT occur in the next 1 hour
1st row. 2nd col: High confidence (81%) that a 10% price increase will NOT occur in the next 1 hour
1st row, 3rd col: High confidence (83%) that a 30% price increase will NOT occur in the next 1 hour
2nd row, 1st col: Low confidence (25%) that a 5% price increase will occur in the next 4 hours
2nd row, 2nd col: Medium confidence (38%) that a 10% price increase will NOT occur in the next 4 hours
2nd row, 3rd col: Medium confidence (44%) that a 30% price increase will NOT occur in the next 4 hours
3rd row, 1st col: Medium confidence (50%) that a 5% price increase will occur in the next 24 hours
3rd row, 2nd col: Low confidence (32%) that a 10% price increase will NOT occur in the next 24 hours
3rd row, 3rd col: Medium confidence (39%) that a 30% price increase will NOT occur in the next 24 hours
1st row, 1st col: High confidence (67%) that a 5% price decrease will NOT occur in the next 1 hour
1st row, 2nd col: High confidence (70%) that a 10% price decrease will NOT occur in the next 1 hour
1st row, 3rd col: High confidence (99%) that a 20% price decrease will NOT occur in the next 1 hour
2nd row, 1st col: Medium confidence (34%) that a 5% price decrease will occur in the next 4 hours
2nd row, 2nd col: Low confidence (27%) that a 10% price decrease will NOT occur in the next 4 hours
2nd row, 3rd col: Medium confidence (64%) that a 20% price decrease will NOT occur in the next 4 hours
3rd row, 1st col: Medium confidence (48%) that a 5% price decrease will occur in the next 24 hours
3rd row, 2nd col: Medium confidence (33%) that a 10% price decrease will occur in the next 24 hours
3rd row, 3rd col: Medium confidence (61%) that a 20% price decrease will NOT occur in the next 24 hours
, 4 hours 
and 24 hours 
.
2. The column label indicating the magnitude of price increase or decrease associated with the prediction, for example +10% 
or -10% 
3. The price increase , price decrease or no threshold not predicted to be met symbols associated with the prediction.
4. The strength or confidence of the prediction, which ranges from 1% to 99% and is represented by a percentage, filled bar and banded label, for example 
> Hōkū price predictions are highly granular, but with some practice you'll learn to:
>
> * **Scan the row** that matches your trading horizon (1h, 4h, or 24h).
> * **Glance across columns** to see how aggressive the forecast is (5% → 30%).
> * **Act on consistent strength** (e.g., *Medium/High* across multiple thresholds).
We're constantly evolving the interface for displaying price predictions and value feedback from our users. Don't hesitate to reach out to the team if you have input on this module.
#### Trend start time
This section shows the start time of the alert in UTC, ISO and your local time as set by your browser.
means 7 of the 9 predicted price movements occurred within the specified timeframes. Similarly, a result of 9/9 
means all 9 predictions were found to be correct.\
These results are calculated automatically from live blockchain data, using real market prices at the exact prediction horizons. More details are shown in the prediction data display when you click a historical alert, which is discussed in the next section.
Check out this video for more information on our backested signal alerts:
{% embed url="
denotes a price increase, the red downward arrow 
denotes a price decrease, and the non-event symbol 
denotes the threshold not being met. Each timeframe and price threshold contains a set of 2 symbols (1 for the predicted price 1 for the actual observed price) , which when match indicate a correct prediction.
> Keep in mind that a prediction can be marked corrected before its time frame has expired. If, for example, a 20% price increase is predicted for the 1 hour, 4 hour and 24 hour timeframes and an actual price increase of 20% occurs in the first hour, then all 3 time frames can be marked correct. However, the opposite scenario cannot occur. If a price threshold has not yet been met, the time frame must fully expire to definitively validate the prediction.
Below are 3 example tables along with corresponding explanations noted from left-to-right, top-to-bottom in the image captions. In each explanation, the green check ✅ indicates a correct prediction, the red X ❌ indicates an incorrect prediction, and clock 🕐 indicates a pending prediction whose timeframe has not expired.
This table shows a **buy alert** prediction that was highly accurate, with only 1 prediction pending.
1st row, 1st col: ✅ +20% in 1 hour was predicted and +46% was observed
1st row, 2nd col: ✅ +50% in 1 hour was NOT predicted and only +46% was observed
1st row, 3rd col: ✅ +200% in 1 hour was NOT predicted and only +46% was observed
2nd row, 1st col: ✅ +20% in 4 hours was predicted and +93% was observed
2nd row, 2nd col: ✅ +50% in 4 hours was predicted and +93% was observed
2nd row, 3rd col: ✅ +200% in 4 hours was NOT predicted and only +93% was observed
3rd row, 1st col: ✅ +20% in 24 hours was predicted and +93% had already been observed in prior timeframes
3rd row, 2nd col: ✅ +50% in 24 hours was predicted and +93% had already been observed in prior timeframes
3rd row, 3rd col: 🕐 +200% in 24 hours was NOT predicted but the timeframe has not expired yet
1st row, 1st col: ❌ -5% in 1 hour was predicted but only -4% was observed
1st row, 2nd col: ❌ -10% in 1 hour was predicted but only -4% was observed
1st row, 3rd col: ❌ -20% in 1 hour was predicted but only -4% was observed
2nd row, 1st col: ✅ -5% in 4 hours was predicted and -21% was observed
2nd row, 2nd col: ✅ -10% in 4 hours was predicted and -21% was observed
2nd row, 3rd col: ✅ -20% in 4 hours was predicted and -21% was observed
3rd row, 1st col: ✅ -5% in 24 hours was predicted and -21% had already been observed in prior timeframes
3rd row, 2nd col: ✅ -10% in 24 hours was predicted and -21% had already been observed in prior timeframes
3rd row, 3rd col: ✅ -20% in 24 hours was predicted and -21% had already been observed in prior timeframes
1st row, 1st col: ❌ +20% in 1 hour was predicted but only +11% was observed
1st row, 2nd col: ❌ +50% in 1 hour was predicted but only +11% was observed
1st row, 3rd col: ✅ +200% in 1 hour was NOT predicted and only +11% was observed
2nd row, 1st col: ❌ +20% in 4 hours was predicted but only +11% was observed
2nd row, 2nd col: ❌ +50% in 4 hours was predicted but only +11% was observed
2nd row, 3rd col: ❌ +200% in 4 hours was predicted but only +11% was observed
3rd row, 1st col: 🕐 +20% in 24 hours was predicted but the timeframe has not expired yet
3rd row, 2nd col: 🕐 +50% in 24 hours was predicted but the timeframe has not expired yet
3rd row, 3rd col: 🕐 +200% in 24 hours was predicted but the timeframe has not expired yet
.jpg?alt=media&token=dc496f9d-43cf-4bbe-b02e-98e2239ed746)
in the left-side button menu.
#### Optional holders subchart
The optional Holders Chart adds an entirely new layer of insight to the price chart by showing how the number of wallets holding a token changes over time. You can turn it on or off using the diamond icon 
found in the upper bar. When enabled, a smooth blue line appears below the main price chart. This line tracks the count of distinct wallets that currently hold the token. Each point represents a moment in time meaning as the number rises, more wallets are accumulating; when it falls, holders are exiting their positions.
#### **Timeframes and date ranges**
You can adjust how much data is shown by changing the chart’s timeframe. Shorter intervals show each candle as just a few minutes of trading, which is useful for fast-moving tokens. Longer intervals show broader trends over days or weeks. Clicking the down arrow on the right will expand the menu to show all available selections.
shown at the bottom of the chart.
#### **Price pairs and info**
At the top of the chart, you’ll see the pair being analyzed.
that when clicked offers a range of different chart types.
.
On the bottom right, you'll also find a series of controls 
to toggle between normal and logarithmic scales, or to view percentage changes instead of price values. These simply change how the data is displayed, not the data itself.
#### **Drawing tools**
On the left side of the chart, you’ll find tools for drawing lines, shapes, or notes.
in the upper right, lets you customize how the chart looks and behaves.
or down 
arrow between the fields to reverse the trade (receive the top token and send the bottom one).
5. **Check live quote & USD estimate.** Below the inputs you’ll see the **estimated rate** (e.g., “1 ETH ≈ 0.03 WBTC”) and dollar estimates for each side. These update automatically as prices move.
6. **Verify settings (slippage & preferences).** Open the 
icon to set **slippage tolerance** and other preferences. A tighter slippage protects you from price moves but may cause the swap to fail in volatile markets; a wider slippage increases the chance of filling but can result in a slightly worse price.
7. **Check Fees, gas, and safety.** The widget shows gas/cost estimates and may warn about high **price impact** or low liquidity. Review these before confirming, especially on new or thinly traded tokens.
8. **Execute the trade.** Click Swap, confirm in your wallet, and wait for the transaction to finalize on-chain. After confirmation, balances update automatically and you’ll see the received token in your wallet. If it’s your first time swapping a token, your wallet will ask you to **approve** the token before you can swap. This is a standard, one-time permission so the router can spend the specified amount.
#### Cross-chain swaps
Cross-chain swaps let you trade tokens between different blockchains all in one step. You don’t need to manually bridge, send, or re-swap your tokens. Everything happens automatically behind the scenes.
To execute a cross-chain swap, first enable that option from within the token selector menu by clicking into either the **From** or **To** token selection box.
A typical TokenSniffer score example
An example of a high-risk token from TokenSniffer.
No Honeypot Detected (Low Risk)
No Honeypot Detected (Medium Risk)
Honeypot Detected (High Risk)
No Honeypot Detected (Unknown Risk)
while the TokenSniffer results are found in the column noted by their logo 
.
Any negative finding is noted by a red check 
, which indicates a potentially malicious or negative contract attribute was found. It's entire row will also be highlighted in red, even if only one provider detected the attribute.
, and execute. For cross-chain or gasless flows, choose the destination chain or sign the gasless intent and complete the trade without leaving the page.
