INDEX
Explanations
information related to film production and filmmakers
New Auto-Interp
Negative Logits
ovol
-0.16
zip
-0.15
виÑĩ
-0.14
atrix
-0.14
егод
-0.14
_MP
-0.14
rowse
-0.14
ohn
-0.14
æĺŁ
-0.14
asher
-0.13
POSITIVE LOGITS
shorts
0.30
Shorts
0.26
feature
0.26
fiction
0.25
short
0.24
Short
0.23
feature
0.21
Feature
0.21
Fiction
0.21
animation
0.21
Activations Density 0.082%