INDEX
Explanations
words and phrases relating to pretentiousness
New Auto-Interp
Negative Logits
alth
-0.18
ered
-0.17
¹Ħ
-0.16
oya
-0.15
cers
-0.14
gun
-0.14
cliff
-0.14
icing
-0.14
oy
-0.14
aling
-0.14
POSITIVE LOGITS
prav
0.17
871
0.16
اÙĩر
0.16
rawl
0.15
pret
0.15
važ
0.14
loid
0.14
zsche
0.14
νÏİ
0.14
IBUTES
0.14
Activations Density 0.010%