INDEX
Explanations
references to children or child-related themes
New Auto-Interp
Negative Logits
\{\\-0.67
שוליים
-0.61
Sorensen
-0.60
SBATCH
-0.57
rington
-0.54
bres
-0.53
сиона
-0.53
Correspond
-0.53
waitKey
-0.52
vergne
-0.52
POSITIVE LOGITS
child
3.21
Child
2.89
Child
2.75
child
2.71
CHILD
2.69
CHILD
2.25
childs
1.65
Childs
1.52
getChild
1.36
childs
1.21
Activations Density 0.108%