INDEX
Explanations
nominations for film awards
New Auto-Interp
Negative Logits
_uc
-0.16
celebrities
-0.15
733
-0.14
nick
-0.14
celebrity
-0.14
iyim
-0.14
uyo
-0.14
_epi
-0.14
iscard
-0.14
ynchronously
-0.14
POSITIVE LOGITS
categories
0.22
nominations
0.22
awards
0.22
category
0.21
sn
0.20
category
0.20
Best
0.20
nomination
0.19
Oscar
0.19
nods
0.19
Activations Density 0.015%