INDEX
Explanations
mentions of personal interactions or connections
financial data related to box office earnings of films
New Auto-Interp
Negative Logits
NetMessage
-0.33
Pwr
-0.30
RESULTS
-0.28
enei
-0.28
pmwiki
-0.27
=-=-
-0.27
++++++++++++++++
-0.27
WATCHED
-0.26
slow
-0.26
odynam
-0.26
POSITIVE LOGITS
usional
0.33
sburg
0.30
lycer
0.30
ictionary
0.29
rue
0.28
hower
0.28
wagon
0.28
schild
0.27
ierre
0.27
oking
0.27
Activations Density 10.704%