INDEX
Explanations
names of people, specifically those named "Marie."
mentions of the name "Marie."
New Auto-Interp
Negative Logits
arta
-0.86
yssey
-0.79
aries
-0.79
iances
-0.78
oted
-0.78
istical
-0.76
ifiers
-0.76
iaries
-0.75
iction
-0.75
inosaur
-0.74
POSITIVE LOGITS
lla
0.98
Claire
0.97
Slaughter
0.90
fen
0.77
lette
0.73
Thatcher
0.72
Louise
0.68
Cur
0.66
mater
0.66
Anne
0.63
Activations Density 0.036%