INDEX
Explanations
mentions of countries and regions
New Auto-Interp
Negative Logits
occo
-0.18
adoo
-0.17
ieri
-0.16
amba
-0.15
asher
-0.15
yles
-0.15
ieves
-0.14
udeau
-0.14
mtime
-0.14
aho
-0.14
POSITIVE LOGITS
usp
0.17
-forward
0.16
uf
0.15
ênh
0.15
Morr
0.15
forward
0.15
Mature
0.14
LENGTH
0.14
fre
0.14
imat
0.14
Activations Density 0.062%