INDEX
Explanations
mentions of the name "Abdul" and its variations
New Auto-Interp
Negative Logits
uds
-0.17
abel
-0.17
ensch
-0.16
arity
-0.15
othy
-0.15
yers
-0.15
wort
-0.14
ÐIJÑĢÑħÑĸв
-0.14
inary
-0.14
sx
-0.14
POSITIVE LOGITS
atif
0.22
ÑĢаÑħ
0.21
raz
0.20
raham
0.19
maj
0.18
rah
0.18
lat
0.17
Rahman
0.17
Lat
0.17
basit
0.17
Activations Density 0.006%