INDEX
Explanations
references to significant religious figures and their associated narratives
New Auto-Interp
Negative Logits
Odin
-0.16
Circuit
-0.15
illery
-0.15
Rao
-0.15
ÙĤض
-0.15
navr
-0.14
Phát
-0.14
_DS
-0.14
judge
-0.14
michael
-0.14
POSITIVE LOGITS
Jesus
0.18
Palestinian
0.17
oken
0.17
imson
0.16
Elaine
0.15
Jesus
0.15
Mary
0.15
carp
0.14
baskets
0.14
гал
0.14
Activations Density 0.114%