INDEX
Explanations
references to the "Harry Potter" series and related terms
references to the Harry Potter series and its characters
New Auto-Interp
Negative Logits
incent
-0.76
IGN
-0.64
¿
-0.63
Texas
-0.62
oples
-0.62
ĺħ
-0.61
asio
-0.61
resp
-0.60
PsyNetMessage
-0.60
itol
-0.58
POSITIVE LOGITS
Potter
1.07
Gand
0.93
Dumbledore
0.92
ebook
0.88
uggle
0.87
loo
0.84
Snape
0.83
wra
0.83
agall
0.82
Hogwarts
0.82
Activations Density 0.069%