INDEX
Explanations
expressions of religious beliefs and teachings
New Auto-Interp
Negative Logits
Ran
-0.17
Mahmoud
-0.16
Ch
-0.15
Seth
-0.15
Armenian
-0.15
ksen
-0.15
Mohammed
-0.14
asing
-0.14
Ach
-0.14
Church
-0.14
POSITIVE LOGITS
Al
0.18
Hij
0.17
al
0.17
alat
0.17
격
0.15
Gem
0.15
Narrated
0.15
iddet
0.15
.qt
0.15
trá»Ŀi
0.14
Activations Density 0.415%