INDEX
Explanations
indications of genre and content ratings in media
New Auto-Interp
Negative Logits
äºĪ
-0.15
ILLE
-0.15
itta
-0.15
emin
-0.14
ummer
-0.14
erty
-0.14
ynam
-0.14
_Abstract
-0.14
Stre
-0.13
idth
-0.13
POSITIVE LOGITS
Uncategorized
0.17
Miscellaneous
0.15
Other
0.15
tv
0.14
ecer
0.14
Undefined
0.14
ÑĩеÑĢ
0.14
OTHER
0.13
"+"
0.13
(Unknown
0.13
Activations Density 0.111%