INDEX
Negative Logits
Gir
-0.08
realizar
-0.08
futuristic
-0.07
nade
-0.07
engen
-0.07
upgrade
-0.07
sadrž
-0.07
humanities
-0.07
-0.07
monetize
-0.07
POSITIVE LOGITS
wé
0.08
lum
0.08
lum
0.08
besproken
0.07
.Scope
0.07
bowls
0.07
канц
0.07
rice
0.07
arguing
0.07
Thanksgiving
0.07
Activations Density 0.003%