Feature #80
Fires on “n” (not labeled yet: read the examples)
- Fires on
- 1.27% of tokens
- Mostly in
- agent
- Layer
- after block 4
Where it fires
- agent 54%
- python 37%
- story 6%
- chat 2%
- worksheet 1%
Makes the model say
Thankn named shiny * BlesR
Makes it not say
One! when coming passed come to run
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
story 3.38surprised because it hadn't taken
-
story 2.67sad that Spot had been bad, but he was relieved that he hadn't gotten sick
-
python 2.63<|bos|># main.py⏎def evens(nums):⏎ return [n for n in nums
-
python 2.62main.py⏎def only_even(nums):⏎ return [n for n in nums
-
python 2.62main.py⏎def keep_even(nums):⏎ return [n for n in nums
-
story 2.58Mummy, but he still felt a little frustrated that the lemon hadn't fit in the
-
story 2.54so sad. It thought it had made a friend. But it hadn't. The child
-
agent 2.5py<|arg|>content=def only_even(nums):⏎ return [n for n in nums
-
python 2.48.⏎⏎```python⏎def evens(nums):⏎ return [n for n in nums
-
python 2.48⏎⏎```python⏎def evens(nums):⏎ return [n for n in nums
-
python 2.47items.py⏎def only_even(nums):⏎ return [n for n in nums
-
python 2.46.⏎⏎```python⏎def evens(nums):⏎ return [n for n in nums