INDEX
Explanations
emotional states or descriptions relating to satisfaction and disappointment
New Auto-Interp
Negative Logits
Ïħνα
-0.17
zier
-0.16
Ìģc
-0.14
DDL
-0.14
âm
-0.14
ænd
-0.14
unct
-0.13
calar
-0.13
èĬ
-0.13
utex
-0.13
POSITIVE LOGITS
comm
0.16
eger
0.15
Uploaded
0.15
go
0.14
ÑĻ
0.14
Vir
0.14
pch
0.14
COMM
0.14
frank
0.14
ry
0.14
Activations Density 0.095%