INDEX
Explanations
names of individuals, particularly in a legal or political context
New Auto-Interp
Negative Logits
ccess
-0.17
ialect
-0.17
verbatim
-0.16
apyrus
-0.16
iminal
-0.16
ilogy
-0.15
aternity
-0.15
rchive
-0.15
odiac
-0.15
posite
-0.15
POSITIVE LOGITS
said
0.32
says
0.26
man
0.25
stein
0.25
field
0.25
baugh
0.24
owitz
0.24
feld
0.23
son
0.23
off
0.23
Activations Density 0.067%