Feature #1775
Fires on “ we” (not labeled yet: read the examples)
- Fires on
- 0.48% of tokens
- Mostly in
- python
- Layer
- after block 4
Where it fires
- python 65%
- agent 24%
- story 6%
- chat 4%
- worksheet 2%
Makes the model say
def_Nofrom⏎ (a`
Makes it not say
words surprise learned Now],Sara next brought
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
agent 3.97webfetch
-
agent 3.97webfetch
-
agent 3.97webfetch
-
agent 3.97webfetch
-
agent 3.97websearch
-
agent 3.97websearch
-
agent 3.97websearch
-
agent 3.97websearch
-
agent 3.97websearch
-
agent 3.97webfetch
-
python 2.86the Python files in this project.<|assistant_end|><|bos|># app.py⏎def half(x
-
python 2.63The answer is 494.<|assistant_end|><|bos|># main.py⏎def how_many