Feature #1652
Fires on “ ” (not labeled yet: read the examples)
- Fires on
- 0.18% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 44%
- worksheet 26%
- story 12%
- python 9%
- chat 8%
Makes the model say
6 looked9 startedSorry8 strong wore
Makes it not say
== sentence filled]ont ballsasedise
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
story 1.49dy had a special job to do. He wanted to make an old automobile
-
worksheet 1.29Python file: `main.py`.<|assistant_end|><|bos|>I need to know 7 + 3
-
worksheet 1.2714, 8]⏎```<|assistant_end|><|bos|>I need to know 9790
-
agent 1.26test_arith.py<|arg|>oldString=positive<|arg|>newString=is_positive
-
agent 1.25<|arg|>path=script.py<|arg|>oldString=SIZE = 7<|arg|>newString=SIZE =
-
agent 1.23path=hello.py<|arg|>oldString= SIZE = 4<|arg|>newString=SIZE =
-
worksheet 1.22py` and `arith.py`.<|assistant_end|><|bos|>I need to know 65 +
-
agent 1.21path=mathlib.py<|arg|>oldString= result = 0<|arg|>newString= result =
-
worksheet 1.2acc + i⏎ return acc⏎```⏎<|bos|>I need to know 950 +
-
worksheet 1.19ops.py`, line 1.<|assistant_end|><|bos|>I need to know 6 + 4
-
agent 1.19=test_calc.py<|arg|>oldString=absolute<|arg|>newString=magnitude<|arg|>
-
story 1.18⏎Their mom was very sad and disappointed. She said they were naughty and rude