INDEX
Explanations
proper nouns, particularly names of individuals and locations
New Auto-Interp
Negative Logits
thon
-0.18
vens
-0.15
chten
-0.15
alcon
-0.15
mate
-0.15
ensi
-0.15
etry
-0.15
orida
-0.15
708
-0.15
ifice
-0.14
POSITIVE LOGITS
prem
0.16
_family
0.15
brothers
0.15
å§ĵ
0.15
Brothers
0.15
Geb
0.15
Sing
0.15
:"-"`↵
0.15
family
0.14
NgModule
0.14
Activations Density 0.875%