INDEX
Explanations
phrases that refer to contemporary or modern contexts
New Auto-Interp
Negative Logits
ammers
-0.17
mere
-0.15
iner
-0.15
stab
-0.15
dale
-0.14
erson
-0.14
FuÃŁ
-0.14
ableObject
-0.14
mere
-0.14
ngr
-0.14
POSITIVE LOGITS
ry
0.16
zon
0.15
colleg
0.15
تØŃص
0.15
omed
0.15
ónico
0.14
omial
0.14
alex
0.14
otto
0.14
ucch
0.14
Activations Density 0.019%