INDEX
Explanations
mentions of the word 'Dad'
references to paternal figures
New Auto-Interp
Negative Logits
atility
-0.85
CONT
-0.79
Topics
-0.76
Flavoring
-0.72
76561
-0.71
rawdownloadcloneembedreportprint
-0.69
atile
-0.67
largeDownload
-0.67
isites
-0.67
lihood
-0.66
POSITIVE LOGITS
dad
0.90
patriarch
0.89
daddy
0.88
Dad
0.85
hesis
0.84
Dad
0.83
father
0.83
liest
0.81
iji
0.80
kson
0.76
Activations Density 0.011%