Feature #1978
Fires on “ has” (not labeled yet: read the examples)
- Fires on
- 0.89% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 36%
- python 29%
- worksheet 17%
- chat 13%
- story 5%
Makes the model say
_( exclamationoldString gets()` typoure
Makes it not say
c little a mom wind other⏎ m
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
python 3.41import keep_even⏎⏎print(keep_even
-
worksheet 3.32rag she had been playing with was never seen again.<|bos|>Ben has 23 flowers
-
worksheet 3.19+ 12 = 80126.⏎Ben has 326
-
python 3.13from text import count_vowels⏎from helpers import subtract⏎⏎print(count_vowels
-
worksheet 3.1<|assistant_end|><|bos|>Tom has 872
-
worksheet 3.09add 2 and 1, you get 3.<|bos|>Anna has 210
-
python 3.0543<|think_end|>The answer is 43.<|assistant_end|><|bos|># opencode.json⏎{
-
python 3.05I only know how to tell stories and add numbers.<|assistant_end|><|bos|># opencode.json⏎{
-
worksheet 3.047852 = 15316⏎Ben has 14 apples
-
worksheet 3.046 + 2 = 40858.⏎Tom has 743
-
python 3.0426<|think_end|>The answer is 26.<|assistant_end|><|bos|># opencode.json⏎{
-
worksheet 3.04154<|assistant_end|><|bos|>Tom has 243