INDEX
Negative Logits
peated
-0.08
plagiarism
-0.06
Merry
-0.06
speech
-0.06
мовір
-0.06
ustomer
-0.06
.new
-0.06
feat
-0.06
duro
-0.06
Kle
-0.06
POSITIVE LOGITS
0.07
kodu
0.07
xEB
0.07
.']
0.07
출
0.07
eligible
0.07
Calc
0.06
Compliance
0.06
NY
0.06
vüc
0.06
Activations Density 0.010%