INDEX
Negative Logits
Ꮬ
0.42
ILabel
0.41
চ্ছুক
0.39
রামর্শ
0.39
ेक्स
0.38
🔐
0.38
ци
0.38
멤버
0.37
ქმ
0.37
Scoped
0.37
POSITIVE LOGITS
surprising
1.83
unexpected
1.78
überras
1.71
surprise
1.67
sorprend
1.66
surprises
1.63
surprised
1.62
unexpected
1.59
inesper
1.55
surpre
1.55
Activations Density 0.155%