INDEX
Explanations
people's names
references to notable individuals, particularly in the context of Jewish history and culture
New Auto-Interp
Negative Logits
cream
-0.77
rup
-0.74
ny
-0.73
llan
-0.72
nel
-0.71
heart
-0.71
ther
-0.70
cream
-0.70
cap
-0.69
hands
-0.68
POSITIVE LOGITS
iries
0.79
ILA
0.79
sbm
0.79
iry
0.79
asca
0.77
atched
0.76
SPONSORED
0.75
yrinth
0.74
ailed
0.73
inances
0.73
Activations Density 0.034%