INDEX
Negative Logits
Circle
0.45
والذي
0.44
~(~)
0.42
ஒன்றை
0.42
ALWAYS
0.40
Always
0.40
cercle
0.40
クレジットカード
0.40
Simply
0.39
마치
0.39
POSITIVE LOGITS
examined
0.48
suspected
0.45
suspicious
0.44
examined
0.42
sag
0.40
розгля
0.39
zyst
0.38
examine
0.37
riez
0.37
compute
0.37
Activations Density 0.000%