INDEX
Explanations
mentions of the word "child" or variations of it
words related to children or childhood
New Auto-Interp
Negative Logits
andise
-0.90
Yates
-0.70
ãĤ®
-0.70
Dragonbound
-0.69
Curry
-0.69
FUL
-0.67
SOURCE
-0.66
CHR
-0.65
Chou
-0.61
okin
-0.60
POSITIVE LOGITS
erers
0.97
reth
0.89
enstein
0.83
ered
0.83
ild
0.82
ering
0.80
er
0.79
roid
0.78
doms
0.78
rag
0.78
Activations Density 0.040%