INDEX
Explanations
references to children and child-related themes
New Auto-Interp
Negative Logits
שוליים
-0.96
RTN
-0.70
,:),
-0.67
Commission
-0.66
Gentlemen
-0.66
erreichen
-0.65
énario
-0.64
hombres
-0.63
uomini
-0.62
\}\\
-0.62
POSITIVE LOGITS
child
3.32
Child
3.14
Child
2.92
child
2.88
CHILD
2.88
CHILD
2.56
childs
1.99
Childs
1.87
childs
1.68
kid
1.64
Activations Density 0.061%