INDEX
Explanations
references to the religion Islam
mentions of Islam
New Auto-Interp
Negative Logits
Rober
-0.74
berries
-0.72
TY
-0.69
Seah
-0.68
asper
-0.67
WD
-0.66
Member
-0.66
heights
-0.64
PsyNetMessage
-0.63
LEASE
-0.63
POSITIVE LOGITS
ophobic
1.64
ophobia
1.57
ophob
1.29
abad
1.10
ification
0.95
ization
0.94
ics
0.94
oph
0.93
icals
0.92
zai
0.90
Activations Density 0.018%