INDEX
Explanations
expressions of emotional intensity or strong feelings
New Auto-Interp
Negative Logits
"
-0.23
s
-0.21
ï¼ļ"
-0.19
'
-0.18
'nin
-0.18
Ùĩ
-0.17
-"
-0.16
("-0.16
ooth
-0.15
..."
-0.15
POSITIVE LOGITS
ing
0.24
Ø©
0.19
(
0.18
er
0.17
“[
0.17
ed
0.17
页éĿ¢åŃĺæ¡£å¤ĩ份
0.16
“
0.15
,”
0.15
ehr
0.15
Activations Density 0.042%