INDEX
Negative Logits
Minor
-0.08
minor
-0.08
uitzonder
-0.07
том
-0.07
Minor
-0.07
만
-0.07
ാറ
-0.07
얼
-0.07
umin
-0.07
causes
-0.07
POSITIVE LOGITS
ours
0.09
Yours
0.08
Beck
0.08
Jub
0.08
Nk
0.08
yours
0.08
Natalie
0.08
gị
0.08
ikaw
0.07
咪
0.07
Activations Density 0.010%