INDEX
Explanations
words and phrases related to nobility, might, and worthiness
New Auto-Interp
Negative Logits
uality
-0.14
ish
-0.14
ters
-0.14
avid
-0.14
ivate
-0.14
ated
-0.14
aded
-0.14
лекÑģанд
-0.14
åĸľ
-0.14
nir
-0.13
POSITIVE LOGITS
deed
0.17
deeds
0.16
indeed
0.16
predecess
0.16
allest
0.16
kest
0.15
estic
0.15
urdy
0.15
ioc
0.14
สาย
0.14
Activations Density 0.080%