INDEX
Explanations
mentions of the name "Anna"
mentions of the substring "na"
New Auto-Interp
Negative Logits
neys
-0.79
library
-0.70
lasses
-0.70
Cosponsors
-0.69
ienced
-0.69
layer
-0.68
wolves
-0.68
omez
-0.67
UID
-0.67
mop
-0.66
POSITIVE LOGITS
eus
1.27
uthor
1.21
isance
0.97
vel
0.92
ples
0.91
veland
0.89
ïve
0.87
ven
0.80
uth
0.80
wn
0.80
Activations Density 0.021%