INDEX
Negative Logits
reportedly
0.75
purportedly
0.59
appear
0.59
notoriously
0.54
supposedly
0.54
nhằm
0.53
allegedly
0.52
inform
0.52
we
0.52
according
0.52
POSITIVE LOGITS
says
0.75
agrees
0.69
iertos
0.68
รีย
0.65
LensFlare
0.63
丷
0.63
nieces
0.62
Montessori
0.61
acariy
0.61
geven
0.60
Activations Density 0.006%