Feature #2931
Fires on “ ex” (not labeled yet: read the examples)
- Fires on
- 0.55% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 83%
- story 10%
- python 3%
- chat 3%
- worksheet 1%
Makes the model say
edanceicetail startedan
Makes it not say
(-ultipliesfrom example( Lily Can
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
agent 6.13execute<|system_end|>
-
agent 6.13execute<|system_end|>
-
agent 6.13execute<|system_end|>
-
story 6.13extra, leave some
-
agent 6.13execute<|system_end|>
-
agent 6.13execute<|system_end|>
-
agent 4.86, execute<|system_end|>
-
agent 4.86, execute<|system_end|>
-
agent 4.86, execute<|system_end|>
-
agent 4.86, execute<|system_end|>
-
agent 4.86, execute<|system_end|>
-
agent 4.86, execute<|system_end|>