INDEX
Explanations
proper names and foreign words
New Auto-Interp
Negative Logits
ung
0.81
at
0.75
ure
0.74
ong
0.72
ل
0.71
י
0.71
ον
0.69
ë
0.68
ly
0.68
ng
0.67
POSITIVE LOGITS
Викто
0.57
века
0.57
Développement
0.57
climático
0.56
Reinigung
0.55
Bharatiya
0.55
século
0.55
профессиона
0.54
Departamento
0.54
professionnel
0.54
Activations Density 0.006%