INDEX
Explanations
special characters or symbols often used in social media contexts or informal communications
New Auto-Interp
Negative Logits
ioned
-0.74
phe
-0.73
itar
-0.71
Kling
-0.71
jet
-0.68
itarian
-0.66
Franch
-0.66
maid
-0.66
enegger
-0.66
sonian
-0.65
POSITIVE LOGITS
Į
1.92
İ
1.78
ĵ
1.69
Ķ
1.68
Ĵ
1.67
¥ŀ
1.59
ı
1.57
IJ
1.57
ĻĤ
1.57
ħ
1.56
Activations Density 0.020%