INDEX
Negative Logits
黄金
-0.09
golden
-0.09
ophi
-0.08
AGM
-0.08
Golden
-0.08
伟
-0.08
Golden
-0.08
Karls
-0.07
золот
-0.07
Gap
-0.07
POSITIVE LOGITS
nonsense
0.08
પાક
0.08
inations
0.08
alahan
0.08
mainly
0.08
naman
0.08
likewise
0.07
άλιστα
0.07
unnecessarily
0.07
abruptly
0.07
Activations Density 0.002%