INDEX
Explanations
elements related to emotional or expressive content in text
New Auto-Interp
Negative Logits
\{\\-0.53
StoryboardSegue
-0.52
存于互联网档案馆
-0.49
ambilan
-0.46
AddTagHelper
-0.46
aitlin
-0.46
)?;
-0.44
eadilan
-0.44
__":
-0.44
těte
-0.43
POSITIVE LOGITS
emoji
1.18
emoticon
1.08
emojis
1.04
Emo
1.02
emo
0.97
emoji
0.94
Emo
0.94
Emoji
0.93
emo
0.87
smiley
0.85
Activations Density 0.211%