INDEX
Negative Logits
chocolate
-0.09
োৱা
-0.09
Америка
-0.09
Chrome
-0.08
delegation
-0.08
Registration
-0.08
registration
-0.08
(theta
-0.08
word
-0.08
Gregorian
-0.08
POSITIVE LOGITS
EIF
0.16
FOX
0.16
STAT
0.16
VEG
0.15
USP
0.15
Bax
0.15
Akt
0.15
GAP
0.14
EIF
0.14
hn
0.14
Activations Density 0.016%