INDEX
Explanations
references to Christianity and related concepts
New Auto-Interp
Negative Logits
china
-0.18
ervoir
-0.16
IES
-0.16
Christianity
-0.15
dk
-0.15
elon
-0.15
ikip
-0.15
inspace
-0.15
inch
-0.15
ULAR
-0.14
POSITIVE LOGITS
ity
0.27
ized
0.25
Bale
0.21
-Muslim
0.20
izing
0.20
ize
0.19
ITY
0.18
å¾Ĵ
0.18
ities
0.17
ization
0.17
Activations Density 0.012%