INDEX
Explanations
instances of storytelling and narrative elements
New Auto-Interp
Negative Logits
narr
-0.21
narrator
-0.19
Narr
-0.18
Narr
-0.17
narration
-0.16
tell
-0.16
tell
-0.15
elines
-0.14
theses
-0.14
Tell
-0.14
POSITIVE LOGITS
story
0.29
Stores
0.22
stores
0.22
tale
0.21
har
0.21
moving
0.21
Stores
0.20
Story
0.20
Store
0.20
true
0.19
Activations Density 0.056%