Feature #1344
Fires on “ better” (not labeled yet: read the examples)
- Fires on
- 0.26% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 78%
- story 15%
- chat 5%
- python 1%
- worksheet 1%
Makes the model say
to " qu README Just up stwords
Makes it not say
} Pythonprint divisible Tom laterdouble
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
story 3.88time and never felt nosy again. Instead, he learned that it's better to just relax
-
agent 3.53test_mathlib.py (3 replacements)<|tool_end|><|assistant_start|>Renamed `cubed` to `cubed_
-
agent 3.49<|tool_start|>Edited lists.py (1 replacement)<|tool_end|><|assistant_start|>Renamed `head` to `head_
-
story 3.48to celebrate their new friendship. Tom and Jerry learned that it is better to be friends and
-
agent 3.44<|tool_start|>Edited mathlib.py (1 replacement)<|tool_end|><|assistant_start|>Renamed `odd` to `odd_
-
chat 3.42and Max were not friends. They both learned that sometimes, it is better to share and be
-
agent 3.41<|tool_start|>Edited lists.py (1 replacement)<|tool_end|><|assistant_start|>Renamed `count` to `how_
-
agent 3.39<|tool_start|>Edited script.py (2 replacements)<|tool_end|><|assistant_start|>Renamed `factorial` to `my_
-
story 3.38wise words, Pete and Tom learned the lesson that it is better for friends to share
-
agent 3.36<|tool_start|>Edited listlib.py (1 replacement)<|tool_end|><|assistant_start|>Renamed `tail` to `my_
-
story 3.35yarn. The moral of the story is that sometimes, it's better to share and be
-
story 3.32clothes. In the end, they became friends and learned that it is better to work together than