INDEX
Explanations
names of entities, particularly people and organizations
New Auto-Interp
Negative Logits
koa
-0.16
inz
-0.15
Armour
-0.14
families
-0.14
onu
-0.14
çµ
-0.13
Klopp
-0.13
tero
-0.13
анов
-0.13
.shtml
-0.13
POSITIVE LOGITS
undy
0.18
à¥įà¤ł
0.17
пи
0.16
ière
0.15
stÅĻed
0.14
пов
0.14
olon
0.14
ibold
0.14
Ìģ
0.14
Dion
0.14
Activations Density 0.038%