INDEX
Negative Logits
respectivamente
-0.89
enfans
-0.81
natten
-0.79
amitié
-0.79
midnight
-0.77
respectivement
-0.77
touristes
-0.75
normaux
-0.75
artesanales
-0.72
rispet
-0.70
POSITIVE LOGITS
[]:
0.59
Giles
0.52
tas
0.51
trunks
0.50
tle
0.49
letters
0.48
RTL
0.48
tl
0.47
ness
0.47
alt
0.47
Activations Density 0.087%