INDEX
Explanations
proper nouns
mentions of the surname "Rivera."
New Auto-Interp
Negative Logits
orate
-0.89
rity
-0.88
urated
-0.85
rified
-0.84
ories
-0.81
ropolitan
-0.77
mble
-0.77
eor
-0.77
etsy
-0.77
rification
-0.76
POSITIVE LOGITS
DragonMagazine
0.88
olla
0.79
backer
0.79
Rivera
0.75
dale
0.74
River
0.70
Papers
0.69
anches
0.68
melon
0.68
cki
0.66
Activations Density 0.025%