Feature #3659
Fires on “ ex” (not labeled yet: read the examples)
- Fires on
- 0.29% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 89%
- story 8%
- python 2%
- chat 1%
- worksheet 0%
Makes the model say
e len <Sorry maybe enough miniCreated
Makes it not say
find saw, meet found+ friends always
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
agent 2.98webfetch, websearch, write, execute<|system_end|>
-
agent 2.96webfetch, websearch, write, execute,
-
agent 2.95webfetch, websearch, write, execute,
-
agent 2.95webfetch, websearch, write, execute<|system_end|>
-
agent 2.94webfetch, websearch, write, execute<|system_end|>
-
agent 2.94webfetch, websearch, write, execute<|system_end|>
-
agent 2.93webfetch, websearch, write, execute<|system_end|>
-
agent 2.93webfetch, websearch, write, execute<|system_end|>
-
agent 2.93webfetch, websearch, write, execute<|system_end|>
-
agent 2.93webfetch, websearch, write, execute<|system_end|>
-
agent 2.92webfetch, websearch, write, execute<|system_end|>
-
agent 2.92webfetch, websearch, write, execute<|system_end|>