INDEX
Explanations
references to Islamic teachings and figures, particularly Prophet Muhammad
New Auto-Interp
Negative Logits
शन
-0.16
fait
-0.14
.chars
-0.14
Thorn
-0.14
PointerType
-0.13
омÑĸ
-0.13
stead
-0.13
401
-0.13
ney
-0.13
slides
-0.13
POSITIVE LOGITS
peace
0.29
peace
0.25
Peace
0.24
Peace
0.24
عÙĦÙĬÙĩ
0.23
صÙĦÙī
0.22
ÙĪØ³ÙĦÙħ
0.21
(pb
0.17
SW
0.17
SWT
0.17
Activations Density 0.051%