INDEX
Explanations
names of countries and geographical regions
New Auto-Interp
Negative Logits
ÑĮе
-0.15
bourg
-0.15
ype
-0.15
commercially
-0.14
roupon
-0.14
ecret
-0.14
uur
-0.14
еÑĢом
-0.14
ibir
-0.14
æ·¡
-0.14
POSITIVE LOGITS
Tiny
0.16
iesz
0.15
/tiny
0.14
اÙģØª
0.14
richt
0.14
Sez
0.13
à¸ļาà¸Ĺ
0.13
-valu
0.13
ITTER
0.13
Tiny
0.13
Activations Density 0.015%