Feature #105
Fires on “,” (not labeled yet: read the examples)
- Fires on
- 1.44% of tokens
- Mostly in
- story
- Layer
- after block 4
Where it fires
- story 47%
- agent 42%
- chat 8%
- python 2%
- worksheet 1%
Makes the model say
Finally until,Finally set to one man
Makes it not say
pathiverll noise adds /du"))
Strongest examples
On text the dictionary never trained on. The underlined token is where it fires most.
-
story 3.75and then seek me." Ben says, "OK. One, two, three..." Lily
-
story 3.38very excited and started to count right away. He counted one, two, three, four,
-
chat 3.15pumpkin out, but it was too tight. She tried again and again, but the pumpkin would
-
story 3.1ly a little bit. On the count of three. One, two, three!"⏎Sara
-
story 2.86to number their steps. They took turns counting one, two, three, and so
-
story 2.81. They count the blocks as they add them. "One, two, three, four,
-
story 2.76The bird did not give up. He tried again and again. Finally, the bird got the
-
story 2.75the stairs. She counted them as she went. One, two, three, four,
-
story 2.74tried to balance on it. He was persistent and tried again and again.⏎Finally
-
chat 2.73get the cake. But he was too small. Tim tried and tried, but he could not
-
story 2.71't look." Lily closed her eyes and counted. "One, two, three, four,
-
story 2.71the chair, but it was too high. He tried again and again, but he could not