INDEX
Explanations
references to specific battles and their significance
New Auto-Interp
Negative Logits
ROUND
-0.15
getP
-0.14
?action
-0.14
座
-0.14
rire
-0.14
óc
-0.14
Gren
-0.14
otton
-0.14
éal
-0.13
ffee
-0.13
POSITIVE LOGITS
Ãłn
0.15
Andres
0.15
ï¸ı
0.14
аннÑĭ
0.14
odo
0.13
Fra
0.13
asics
0.13
Sly
0.13
Clo
0.13
Aud
0.13
Activations Density 0.042%