INDEX
Explanations
proper names related to individuals named Alexander
mentions of the name "Alexander."
New Auto-Interp
Negative Logits
zee
-0.97
kered
-0.87
elling
-0.82
eless
-0.81
neys
-0.81
eling
-0.80
eful
-0.80
rosse
-0.79
atical
-0.78
eled
-0.78
POSITIVE LOGITS
Gust
0.84
Alexander
0.78
Hamilton
0.77
Calder
0.76
opoulos
0.75
Wang
0.75
Cock
0.74
sson
0.73
Graham
0.72
Payne
0.71
Activations Density 0.010%