Feature #869
Fires on “ backwards” (not labeled yet: read the examples)
- Fires on
- 0.59% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 93%
- chat 3%
- python 2%
- story 2%
- worksheet 0%
Makes the model say
<|tool_call_end|> help Python]))!") forgivereplaceAllpath
Makes it not say
likedCan meThat⏎orAdd The
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
agent 3.271<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def min_item<|tool_call_end|><|assistant_end|>
-
agent 3.151<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def backwards<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 3.15is defined<|user_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def cube<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 3.12code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def power<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 3.05with code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def minus<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 2.98<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def sum_to<|tool_call_end|><|assistant_end|>
-
agent 2.98<|user_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def has_item<|tool_call_end|><|assistant_end|>
-
agent 2.93with code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def reverse<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 2.92with code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def magnitude<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 2.91with code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def decrement<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 2.91with code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def backwards<|tool_call_end|><|assistant_end|><|tool_start|>Found
-
agent 2.91with code 1<|tool_end|><|assistant_start|><|tool_call_start|>grep<|arg|>pattern=def flip<|tool_call_end|><|assistant_end|><|tool_start|>Found