INDEX
Explanations
instances of the word "cringe" or its variations in various contexts
New Auto-Interp
Negative Logits
ards
-0.14
tar
-0.14
ÄĻd
-0.14
Keeper
-0.14
anine
-0.14
Bez
-0.14
estro
-0.14
avis
-0.14
oming
-0.13
ieg
-0.13
POSITIVE LOGITS
cr
0.31
Cr
0.26
(cr
0.20
utch
0.19
ITICAL
0.19
inge
0.17
ystal
0.17
onen
0.16
udo
0.16
acker
0.16
Activations Density 0.015%