INDEX
Explanations
references to familial relationships and lineage
New Auto-Interp
Negative Logits
Autoritní
-0.52
znaj
-0.52
IntoConstraints
-0.49
bukkit
-0.48
ologico
-0.48
观的
-0.46
visst
-0.46
igu
-0.45
سطس
-0.44
ndy
-0.44
POSITIVE LOGITS
Daughters
0.99
daughters
0.96
progeny
0.94
Daughter
0.94
father
0.92
parents
0.91
daughter
0.91
Parents
0.88
sons
0.85
aughters
0.84
Activations Density 0.224%