INDEX
Explanations
components related to theatrical performances and historical events
New Auto-Interp
Negative Logits
putation
-0.16
libc
-0.16
Minister
-0.14
ascar
-0.14
ennon
-0.14
HI
-0.14
otto
-0.14
Santo
-0.14
Colbert
-0.14
ibo
-0.13
POSITIVE LOGITS
BBC
0.21
BBC
0.19
bbc
0.17
broadcaster
0.16
Pur
0.15
.gs
0.15
london
0.15
опол
0.15
urus
0.15
HEN
0.15
Activations Density 0.015%