INDEX
Explanations
references to children and family relationships
New Auto-Interp
Negative Logits
deniz
-0.16
iben
-0.16
Friend
-0.15
Friend
-0.15
unday
-0.14
als
-0.14
idl
-0.14
ancestor
-0.14
andi
-0.13
ẩu
-0.13
POSITIVE LOGITS
whom
0.25
born
0.22
adopted
0.21
twins
0.21
named
0.19
grown
0.19
named
0.19
twin
0.19
Named
0.18
conceived
0.18
Activations Density 0.159%