INDEX
Explanations
words related to children or child-related topics
references to children
New Auto-Interp
Negative Logits
ced
-0.78
comm
-0.70
olulu
-0.68
ihara
-0.66
uncture
-0.61
âĸ¬
-0.60
adena
-0.60
ItemTracker
-0.60
ATIVE
-0.60
CV
-0.59
POSITIVE LOGITS
children
1.23
children
1.04
child
0.95
kids
0.95
Children
0.94
ishly
0.82
Children
0.81
girls
0.81
orphan
0.80
Icar
0.79
Activations Density 0.029%