INDEX
Explanations
names of individuals, particularly those with Arabic origins
New Auto-Interp
Negative Logits
odian
-0.17
arat
-0.16
/goto
-0.15
iker
-0.15
Cour
-0.14
oller
-0.14
ÅĻiv
-0.14
.make
-0.14
odont
-0.14
banka
-0.14
POSITIVE LOGITS
Vul
0.17
Âłje
0.16
iddi
0.15
merc
0.15
vac
0.15
lassen
0.15
ESCO
0.14
enko
0.14
Pilot
0.14
Seznam
0.13
Activations Density 0.023%