INDEX
Explanations
instances of the words "ridiculous" and "absurd" related to criticism or negative commentary
New Auto-Interp
Negative Logits
antry
-0.16
690
-0.16
udad
-0.15
orra
-0.15
_DEFINE
-0.14
åĵ²
-0.14
ÑģпÑĢоÑģ
-0.14
unk
-0.14
oyer
-0.14
anie
-0.14
POSITIVE LOGITS
ochen
0.17
-looking
0.17
ingly
0.16
Ù
0.16
lsen
0.16
ostel
0.14
ummer
0.14
Lair
0.14
awning
0.14
clist
0.13
Activations Density 0.015%