INDEX
Explanations
mentions of the name "Simon."
New Auto-Interp
Negative Logits
gom
-0.15
y
-0.15
sak
-0.15
s
-0.15
eah
-0.14
á»Ļ
-0.14
samp
-0.14
uries
-0.14
ymb
-0.14
Ïħ
-0.14
POSITIVE LOGITS
etta
0.35
etti
0.28
Says
0.25
pj
0.23
ides
0.23
elli
0.22
Cow
0.21
Templ
0.20
cell
0.19
ett
0.19
Activations Density 0.007%