INDEX
Explanations
mentions of the name "Christian" in various contexts
New Auto-Interp
Negative Logits
>"+↵
-0.16
aks
-0.15
ivery
-0.15
arians
-0.15
KNOWN
-0.14
owie
-0.14
USIC
-0.14
Paran
-0.14
(predicate
-0.14
rowse
-0.14
POSITIVE LOGITS
ize
0.18
ized
0.18
ization
0.16
izing
0.16
sted
0.16
m
0.15
ixe
0.15
eum
0.15
Horde
0.15
Bolt
0.15
Activations Density 0.017%