INDEX
Explanations
names and titles related to film awards and nominations
New Auto-Interp
Negative Logits
ALI
-0.17
antro
-0.15
ÑīÑĸ
-0.15
lsru
-0.14
еÑģÑĤе
-0.14
agina
-0.14
еÑĢÑĮ
-0.14
swire
-0.14
/javascript
-0.14
огÑĢа
-0.14
POSITIVE LOGITS
ted
0.22
bor
0.20
nap
0.20
rom
0.19
del
0.18
umb
0.18
biz
0.18
sco
0.18
gre
0.18
locale
0.17
Activations Density 0.019%