Feature #312
Fires on “ Lily” (not labeled yet: read the examples)
- Fires on
- 0.99% of tokens
- Mostly in
- story
- Layer
- after block 4
Where it fires
- story 73%
- agent 14%
- chat 10%
- python 2%
- worksheet 1%
Makes the model say
were are became smiledk went met talking
Makes it not say
andhing It", plus,)) There
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
story 6.0537 = 91540<|bos|>Tom and Mia were best friends.
-
story 5.86wind blew hard. Ollie and Timmy got scared.⏎
-
story 5.51(nums)` returns every number of nums doubled.<|assistant_end|><|bos|>Tom and Lily went to the beach
-
story 5.45in `main.py`.<|assistant_end|><|bos|>Lily and Ben are playing in the
-
story 5.436, 607<|think_end|>607<|assistant_end|><|bos|>Ben and Lily liked to fish with
-
story 5.41: I can tell short stories and add numbers.<|assistant_end|><|bos|>Tom and Mia were playing in the
-
story 5.4collar through the river to clean it." Spot and Cat went to the river
-
story 5.37The red bird and the big blue bird sat in their nest
-
story 5.36to gather sticks and leaves to make a big pile. Max and Lily were having a lot
-
story 5.28507 = 92725.<|bos|>Lily and Tom are friends. They
-
chat 5.13a cat!<|user_end|><|assistant_start|>One day, a big cat and a little dog were playing in the
-
story 5.09⏎Sue and Tom picked a green apple