INDEX
Explanations
words related to dignity and indignation
New Auto-Interp
Negative Logits
Irvine
-0.16
ensch
-0.15
ksam
-0.15
iage
-0.15
skl
-0.15
oucher
-0.14
devil
-0.14
arga
-0.14
ynam
-0.14
mission
-0.14
POSITIVE LOGITS
ificantly
0.24
ificant
0.23
ificance
0.21
itary
0.18
ee
0.18
atures
0.17
y
0.17
ees
0.17
aber
0.17
eous
0.16
Activations Density 0.018%