Feature #987
Fires on “ bad” (not labeled yet: read the examples)
- Fires on
- 1.44% of tokens
- Mostly in
- story
- Layer
- after block 4
Where it fires
- story 65%
- chat 16%
- agent 14%
- python 2%
- worksheet 2%
Makes the model say
ending<|bos|> story end ItomIt yes
Makes it not say
([ needed asked girl):configive stopped
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
story 3.41Now he had plenty of lollipops to eat. What a happy ending!<|bos|>One
-
story 3.22leak again, but it will always be buried in the house.<|bos|><|system_start|>Answer with
-
story 3.22work is important and being lazy won't take you very far in life.<|bos|><|system_start|>tools:
-
story 3.19. They stayed scared and lonely, and the day did not have a happy ending.<|bos|><|system_start|>
-
story 3.15cried. The cat could not help him. Tim's day had a bad ending.<|bos|><|system_start|>
-
story 3.13his lesson the hard way. He must never touch what is not his!<|bos|><|system_start|>You are
-
story 3.12was not fun anymore. They were all sad because the party had a bad ending.<|bos|><|system_start|>
-
story 3.11with money and only buying what you need is a useful life lesson!<|bos|># notes.
-
story 3.03moral of Jan's story: It never hurts to ask for help!<|bos|><|system_start|>tools:
-
story 3.01was lost forever. And that was the bad ending of Tim's story.<|bos|><|system_start|>tools:
-
story 3.0Tom was sad and alone. He learned that being naughty can have a bad ending.<|bos|>8
-
story 2.99She was hurt and cried. The fun day in the yard had a bad ending.<|bos|>Once