Feature #289
Fires on “_” (not labeled yet: read the examples)
- Fires on
- 0.19% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 43%
- story 30%
- python 13%
- chat 12%
- worksheet 1%
Makes the model say
many feeling testown plusFixSorryig
Makes it not say
friends wayjson woods J wouldn=So
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
agent 3.39: from stats import how_many⏎3:
-
agent 3.09OpenCode, a coding agent harness.<|system_end|><|user_start|>Fix the bug in how_many, then check
-
python 2.95494.<|assistant_end|><|bos|># main.py⏎def how_many(items):
-
agent 2.94, a coding agent harness.<|system_end|><|user_start|>Please fix the bug in how_many, then check
-
agent 2.92mean_list(nums)`.<|assistant_end|><|user_start|>Rename the function count to how_many.<|user_end|><|assistant_start|>
-
agent 2.912⏎1: def how_many(items):
-
agent 2.9running in OpenCode, a coding agent harness.<|system_end|><|user_start|>How does how_many work?<|user_end|>
-
agent 2.89, a coding agent harness.<|system_end|><|user_start|>"Explain the function how_many."<|user_end|><|assistant_start|>
-
agent 2.87nums if n % 2 == 0]⏎⏎⏎def how_many(items):
-
agent 2.78running in OpenCode, a coding agent harness.<|system_end|><|user_start|>How does how_many work?<|user_end|>
-
python 2.74.<|assistant_end|><|bos|># test_stats.py⏎from stats import how_many, max_
-
agent 2.71 matches⏎items.py:⏎ Line 5: def how_many(items):