INDEX
Explanations
phrases expressing confusion, frustration, or existential questions
what the hell/wtf expressions
New Auto-Interp
Negative Logits
surla
-0.52
Skocz
-0.49
Viitteet
-0.48
مواليد
-0.44
__':
-0.43
الدراسه
-0.40
-0.39
)))));
-0.38
MENAFN
-0.37
Erreferentziak
-0.37
POSITIVE LOGITS
oa̍t
0.52
到底
0.51
果た
0.50
WTF
0.49
究竟
0.48
Hell
0.47
wtf
0.47
EconPapers
0.46
UnsafeEnabled
0.46
一体
0.45
Activations Density 0.027%