INDEX
Explanations
foreign place names or languages
New Auto-Interp
Negative Logits
ব্যক্তিত্ব
0.81
adhy
0.78
ယာ
0.78
issam
0.77
usan
0.76
physicochemical
0.76
وتن
0.75
éa
0.74
unghi
0.74
microorgan
0.74
POSITIVE LOGITS
Orleans
0.70
español
0.67
Сколько
0.67
чи
0.67
um
0.66
nero
0.65
Alabama
0.64
Florida
0.63
i
0.63
/
0.62
Activations Density 0.233%