INDEX
Explanations
references to influential individuals or organizations in discussions
New Auto-Interp
Negative Logits
ftagPool
-0.40
transQ
-0.38
Rujuakan
-0.36
Descripció
-0.36
nonatomic
-0.36
Personendaten
-0.36
gesagt
-0.35
vodu
-0.35
Dtor
-0.35
stylers
-0.34
POSITIVE LOGITS
added
1.82
Added
1.34
added
1.31
Added
1.28
further
1.20
ADDED
1.15
ajouté
1.14
aggiunto
1.13
adds
1.11
agregó
1.10
Activations Density 0.291%