INDEX
Negative Logits
Smiley
0.74
francis
0.72
обознача
0.72
মনোনীত
0.70
स्थिति
0.69
资格
0.69
utage
0.68
수도
0.68
ennia
0.68
사람
0.65
POSITIVE LOGITS
tore
0.68
förs
0.67
Tong
0.66
scented
0.65
Writers
0.60
svol
0.60
loosening
0.60
derailed
0.59
thanked
0.59
perceived
0.59
Activations Density 0.018%