INDEX
Explanations
mentions of the word "junior."
instances of the word "junior."
New Auto-Interp
Negative Logits
alls
-0.78
igation
-0.77
ãĥķãĤ©
-0.75
ainer
-0.75
eele
-0.72
Ĥİ
-0.72
atche
-0.72
Gutenberg
-0.71
acles
-0.71
roma
-0.69
POSITIVE LOGITS
junior
0.95
mosqu
0.92
iors
0.89
soph
0.84
IOR
0.83
citiz
0.82
adolesc
0.78
delinqu
0.77
omore
0.71
jun
0.70
Activations Density 0.007%