INDEX
Explanations
references to the filmmaker Christopher Nolan
mentions of the director Christopher Nolan
New Auto-Interp
Negative Logits
erences
-0.83
ERAL
-0.77
roots
-0.70
breakers
-0.67
quo
-0.67
externalActionCode
-0.66
ties
-0.65
wife
-0.65
wives
-0.64
Ń·
-0.64
POSITIVE LOGITS
Nolan
0.81
asonic
0.79
unci
0.72
iform
0.72
ufact
0.72
pas
0.71
ning
0.71
icz
0.71
atech
0.70
olan
0.70
Activations Density 0.029%