INDEX
Explanations
elements related to film and filmmaking
New Auto-Interp
Negative Logits
uml
-0.15
Fauc
-0.15
IVEN
-0.14
ällt
-0.14
Singer
-0.14
avid
-0.14
byname
-0.14
èµ·
-0.13
kers
-0.13
COVER
-0.13
POSITIVE LOGITS
feature
0.22
fiction
0.22
director
0.21
Cannes
0.21
shorts
0.20
director
0.19
fiction
0.19
directors
0.18
Feature
0.18
-feature
0.18
Activations Density 0.110%