INDEX
Explanations
references to stylish elements and themes in movies
New Auto-Interp
Negative Logits
Titanic
-0.15
Hogwarts
-0.15
Telescope
-0.15
hower
-0.14
bew
-0.14
hoax
-0.14
ÑĮÑİ
-0.14
prank
-0.14
ume
-0.14
Ses
-0.14
POSITIVE LOGITS
pulp
0.19
Violence
0.18
DEA
0.17
vigil
0.17
adrenal
0.17
Deadpool
0.17
Femme
0.16
violence
0.16
cult
0.16
'action
0.16
Activations Density 0.167%