INDEX
Explanations
mentions of the word "circumcision."
references to circumcision
New Auto-Interp
Negative Logits
uca
-0.83
IELD
-0.81
culosis
-0.72
ARP
-0.69
Mandela
-0.68
ABE
-0.67
Sioux
-0.65
Bey
-0.65
WP
-0.65
ECH
-0.64
POSITIVE LOGITS
uits
1.11
circ
1.02
uit
1.01
umn
0.99
onduct
0.89
adian
0.88
scrib
0.85
uses
0.84
uitous
0.84
Circ
0.84
Activations Density 0.007%