INDEX
Explanations
specific emotional expressions or feelings in text
New Auto-Interp
Negative Logits
ops
-0.15
ay
-0.15
ros
-0.14
Dob
-0.14
обов
-0.14
prot
-0.14
ara
-0.14
pos
-0.14
olg
-0.14
ism
-0.14
POSITIVE LOGITS
ppard
0.20
Äįer
0.16
jedn
0.16
o
0.16
orig
0.16
esktop
0.15
ãĤ
0.15
icÃŃ
0.14
Parm
0.14
reesome
0.14
Activations Density 0.131%