INDEX
Explanations
names of individuals
names of people, particularly those with a specific focus on gender or familial relationships
New Auto-Interp
Negative Logits
querque
-0.80
cffff
-0.79
nown
-0.78
sidx
-0.77
ypes
-0.75
elligence
-0.71
iuses
-0.70
hattan
-0.70
technical
-0.69
*/(
-0.69
POSITIVE LOGITS
Marie
1.26
Louise
1.21
Anne
1.20
Lynn
1.15
Anne
1.14
Kate
1.13
Marie
1.07
Nicole
1.06
Ellen
1.05
Jane
1.04
Activations Density 0.316%