INDEX
Explanations
proper nouns related to a specific person named Sarah
mentions of the name "Sarah."
New Auto-Interp
Negative Logits
awaru
-0.96
nomine
-0.88
ebin
-0.86
ographed
-0.86
essee
-0.80
rosse
-0.77
ugal
-0.75
vernment
-0.74
emonium
-0.74
cffff
-0.73
POSITIVE LOGITS
Palin
1.30
Jane
1.05
McL
0.95
Koen
0.91
Jessica
0.89
Kate
0.88
Connor
0.86
Michelle
0.85
Chal
0.83
Jane
0.83
Activations Density 0.023%