INDEX
Negative Logits
meal
0.59
downright
0.55
blatantly
0.52
lists
0.51
matchs
0.50
earl
0.50
excel
0.48
덟
0.48
سٹر
0.48
oprop
0.48
POSITIVE LOGITS
0.67
0.67
obu
0.67
0.66
0.64
0.64
0.63
}}{\0.61
0.61
0.61
Activations Density 0.099%
meal
downright
blatantly
lists
matchs
earl
excel
덟
سٹر
oprop
obu
}}{\