INDEX
Explanations
elements related to dialogue and narrative style in films
New Auto-Interp
Negative Logits
acular
-0.16
.mvc
-0.15
loh
-0.14
arrera
-0.14
endeavors
-0.14
Centers
-0.13
alen
-0.13
.nasa
-0.13
mund
-0.13
Inbox
-0.13
POSITIVE LOGITS
lit
0.26
Lit
0.24
Lit
0.23
lit
0.22
_lit
0.19
Basil
0.16
æ´²
0.15
USART
0.15
ght
0.15
richt
0.15
Activations Density 0.001%