INDEX
Explanations
references to locations or buildings related to religious or educational institutions
references to the term "temple" in various contexts
New Auto-Interp
Negative Logits
imil
-0.74
20439
-0.74
iability
-0.74
ÑĮ
-0.70
alez
-0.67
leneck
-0.65
sen
-0.64
ives
-0.63
agher
-0.63
nesota
-0.63
POSITIVE LOGITS
temple
0.88
inence
0.88
plates
0.87
temples
0.78
ceremonies
0.78
anus
0.75
bells
0.75
porary
0.74
tsky
0.73
children
0.72
Activations Density 0.021%