INDEX
Explanations
references to Shiite Muslim communities
the names and related mentions of a specific person, likely related to the term "Shi" or similar
New Auto-Interp
Negative Logits
anwhile
-0.85
*/(
-0.85
oration
-0.84
ãģĨ
-0.84
orative
-0.81
é¾įå¥ij士
-0.80
RAFT
-0.73
ment
-0.70
Triumph
-0.70
icative
-0.67
POSITIVE LOGITS
kees
0.93
Shi
0.90
aji
0.84
Xia
0.82
agara
0.79
omi
0.78
aku
0.77
hei
0.76
pton
0.75
qi
0.75
Activations Density 0.002%