INDEX
Explanations
words related to narratives or storytelling
instances of the word "Story" in various contexts
New Auto-Interp
Negative Logits
partic
-0.73
yip
-0.71
inst
-0.69
ktop
-0.66
antis
-0.65
immobil
-0.64
offs
-0.62
indirect
-0.62
around
-0.61
drain
-0.61
POSITIVE LOGITS
Story
3.99
STORY
2.50
Story
2.33
Stories
2.14
story
2.04
story
2.03
stories
1.57
stories
1.43
Narr
1.38
Saga
1.36
Activations Density 0.008%