INDEX
Explanations
the name "Kelly" or variations of it
New Auto-Interp
Negative Logits
ed
-0.23
icana
-0.20
ic
-0.20
oor
-0.19
icia
-0.19
ovich
-0.18
ettes
-0.18
icha
-0.18
opia
-0.18
elim
-0.18
POSITIVE LOGITS
l
0.33
llll
0.28
IGENCE
0.27
t
0.26
eries
0.23
ows
0.23
ings
0.21
inger
0.19
ipsoid
0.19
ipt
0.19
Activations Density 0.064%