INDEX
Explanations
proper names, specifically the name "Anderson"
mentions of the name "Anderson."
New Auto-Interp
Negative Logits
BOOK
-0.78
oppers
-0.74
PER
-0.71
kered
-0.69
misc
-0.69
graded
-0.68
soever
-0.68
oire
-0.66
tml
-0.66
dfx
-0.66
POSITIVE LOGITS
Silva
0.98
Osw
0.87
Cooper
0.84
quist
0.73
Robbins
0.71
iband
0.70
Knox
0.69
sov
0.69
Watts
0.67
Ashe
0.66
Activations Density 0.051%