INDEX
Explanations
names of people and their relationships
New Auto-Interp
Negative Logits
irut
-0.15
ŀ
-0.15
district
-0.14
edir
-0.14
ohana
-0.14
Disclosure
-0.14
_hom
-0.14
ureka
-0.14
.Obj
-0.14
ternet
-0.14
POSITIVE LOGITS
Prince
0.20
Princess
0.20
iani
0.19
prince
0.17
reigning
0.17
princes
0.16
royal
0.16
Consort
0.15
Prince
0.15
princ
0.15
Activations Density 0.054%