INDEX
Explanations
references to the play "King Lear" and its characters
New Auto-Interp
Negative Logits
ç·Ĵ
-0.17
resco
-0.16
îł
-0.16
elines
-0.15
lz
-0.14
byss
-0.14
ูà¹Ī
-0.14
ванов
-0.14
ller
-0.14
داد
-0.14
POSITIVE LOGITS
Jaime
0.16
ĥ
0.15
Bol
0.15
Perc
0.15
æŁ´
0.14
sen
0.14
Stark
0.14
ndo
0.14
Ty
0.14
anik
0.14
Activations Density 0.007%