INDEX
Explanations
female names
names, particularly of individuals
New Auto-Interp
Negative Logits
*/(
-0.82
direction
-0.79
ramid
-0.78
alion
-0.77
riter
-0.77
cffff
-0.72
undai
-0.72
ritic
-0.71
taboola
-0.71
context
-0.70
POSITIVE LOGITS
Mae
1.42
Marie
1.40
Lynn
1.30
Louise
1.29
Leigh
1.25
Anne
1.22
Rae
1.22
Anne
1.21
Marie
1.18
DeVos
1.17
Activations Density 0.221%