INDEX
Explanations
expressions of anger or confrontation
New Auto-Interp
Negative Logits
ⓧ
-0.64
super
-0.57
super
-0.55
Ad
-0.49
OWSKI
-0.49
(;;
-0.48
corazones
-0.47
Super
-0.47
VersionUID
-0.47
side
-0.47
POSITIVE LOGITS
estimés
0.63
webElementXpaths
0.61
IsMutable
0.57
gitter
0.55
GeoNames
0.54
Chham
0.54
uncut
0.53
Activités
0.53
intellectuelle
0.52
coraggio
0.52
Activations Density 0.275%