INDEX
Negative Logits
emd
0.61
arthritis
0.59
McGu
0.57
Unemployment
0.56
ут
0.55
colonialism
0.54
affirming
0.54
iveness
0.54
אר
0.53
omenclature
0.53
POSITIVE LOGITS
erten
0.60
bringen
0.58
ERO
0.56
rera
0.56
ernes
0.56
RIN
0.56
chopped
0.55
multiplied
0.55
catered
0.55
SERV
0.54
Activations Density 0.000%