INDEX
Explanations
mentions of the name "Frank"
New Auto-Interp
Negative Logits
NING
-0.16
ICAL
-0.16
ëĿ½
-0.15
adiens
-0.15
kaar
-0.14
Ñĥнк
-0.14
echa
-0.14
craper
-0.14
estroy
-0.14
672
-0.14
POSITIVE LOGITS
enstein
0.41
fur
0.36
furt
0.35
lin
0.34
fort
0.32
rijk
0.32
lyn
0.31
Sinatra
0.30
ly
0.28
ie
0.28
Activations Density 0.007%