INDEX
Explanations
references to lead roles or lead characters in various contexts
New Auto-Interp
Negative Logits
er
-0.17
ker
-0.16
ADDE
-0.16
gram
-0.16
ucc
-0.16
-deals
-0.15
ialis
-0.15
gem
-0.15
acker
-0.14
ulus
-0.14
POSITIVE LOGITS
lead
0.24
lead
0.23
Lead
0.23
Lead
0.23
chio
0.19
poisoning
0.17
EXEMPLARY
0.16
ÂŃing
0.16
/front
0.16
à¸Ńย
0.16
Activations Density 0.014%