INDEX
Explanations
mentions of family relationships and ancestry
New Auto-Interp
Negative Logits
childs
-0.17
child
-0.17
parenting
-0.16
.child
-0.16
Parenthood
-0.15
egis
-0.15
children
-0.15
child
-0.15
childs
-0.15
åĦ¿
-0.15
POSITIVE LOGITS
Grand
0.59
Grand
0.56
grand
0.52
Grandma
0.51
grand
0.49
grandma
0.47
Gran
0.47
grandfather
0.45
-grand
0.44
gran
0.44
Activations Density 0.456%