INDEX
Explanations
Romanian and related languages
New Auto-Interp
Negative Logits
噫
0.80
فرق
0.75
Học
0.74
Nu
0.73
Ну
0.73
踊
0.70
বাবা
0.70
தலாக
0.68
lei
0.67
loved
0.66
POSITIVE LOGITS
globale
0.64
productive
0.62
impulsive
0.59
endocrine
0.56
izante
0.56
permanente
0.55
istiche
0.55
integrate
0.54
frecuentes
0.53
nette
0.52
Activations Density 0.001%