INDEX
Explanations
mentions of Hebrew language or scripture
New Auto-Interp
Negative Logits
umen
-0.17
βολ
-0.14
ro
-0.14
аÑĢи
-0.14
uria
-0.14
ier
-0.14
Glover
-0.13
biography
-0.13
.Mapper
-0.13
ainer
-0.13
POSITIVE LOGITS
esses
0.17
-American
0.16
ŀĭ
0.15
ijken
0.15
Floating
0.15
zem
0.15
Floating
0.15
ystack
0.14
odge
0.14
-Christian
0.14
Activations Density 0.005%