INDEX
Negative Logits
er
0.63
ii
0.60
t
0.59
)$,
0.59
কে
0.58
inen
0.55
oxide
0.55
ন
0.55
ete
0.54
મ
0.53
POSITIVE LOGITS
Ottoman
0.86
ottoman
0.64
يس
0.54
Ankara
0.54
Ott
0.54
Bursa
0.54
manif
0.53
Baş
0.53
I
0.53
Turkey
0.52
Activations Density 0.001%