INDEX
Explanations
elements related to emotions and personal experiences
Internet slang and informal speech
New Auto-Interp
Negative Logits
;-)
-0.48
SuppressMessage
-0.48
:-)
-0.47
-0.42
ftagPool
-0.42
ویکیپدی
-0.42
;-)
-0.42
最快更新
-0.40
冏
-0.39
:-)
-0.39
POSITIVE LOGITS
ngl
0.63
lmao
0.63
💀
0.58
tryna
0.53
boi
0.50
memes
0.49
lmfao
0.49
idk
0.49
Idk
0.48
vibes
0.48
Activations Density 0.054%