INDEX
Explanations
mentions of children or kids
New Auto-Interp
Negative Logits
LabelTagHelper
-0.74
CrossRef
-0.71
']}
-0.69
Hara
-0.68
lemak
-0.63
batore
-0.63
Cang
-0.62
Vist
-0.61
raborty
-0.60
SND
-0.59
POSITIVE LOGITS
kids
3.42
Kids
2.88
kids
2.81
Kids
2.80
KIDS
2.65
kid
2.45
KIDS
2.23
children
2.17
children
1.84
Kid
1.82
Activations Density 0.062%