INDEX
Explanations
references to familial relationships and genealogy
New Auto-Interp
Negative Logits
Revenir
-0.54
/*
-0.54
createClass
-0.41
">//
-0.41
שוליים
-0.40
IVEREF
-0.39
yym
-0.38
/**
-0.38
WEBPACK
-0.38
AxisAlignment
-0.38
POSITIVE LOGITS
grandson
0.72
grandfather
0.69
grandparents
0.68
nephew
0.68
uncle
0.66
cousin
0.66
grandmother
0.65
grandpa
0.64
aunts
0.64
Grandmother
0.63
Activations Density 0.151%