INDEX
Explanations
elements of criticism and appreciation in film and cultural discussions
New Auto-Interp
Negative Logits
ez
-0.15
ikel
-0.14
qed
-0.14
agma
-0.14
hani
-0.13
orex
-0.13
Impress
-0.13
å¼¥
-0.13
Sür
-0.13
307
-0.13
POSITIVE LOGITS
forever
0.30
changed
0.29
laid
0.28
defined
0.28
revolution
0.27
popular
0.26
Changed
0.26
changed
0.25
defined
0.25
cement
0.24
Activations Density 0.398%