INDEX
Explanations
references to familial relationships, particularly focusing on brothers and kinship
New Auto-Interp
Negative Logits
falgar
-0.53
kulum
-0.53
первых
-0.52
vierge
-0.52
Tembelea
-0.51
JsonFormat
-0.51
onBind
-0.50
maît
-0.48
Վերցված
-0.48
Wikispecies
-0.47
POSITIVE LOGITS
family
1.33
family
1.08
FAMILY
1.03
Family
0.98
Family
0.97
siblings
0.93
familial
0.90
brother
0.89
FAMILY
0.87
sibling
0.86
Activations Density 0.373%