INDEX
Explanations
mentions of the word "Gothic"
references to Gothic architecture or terminology
New Auto-Interp
Negative Logits
Kislyak
-0.70
Cheong
-0.64
assetsadobe
-0.64
andum
-0.64
lished
-0.63
perature
-0.63
Waterloo
-0.62
ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
-0.61
verett
-0.60
aukee
-0.60
POSITIVE LOGITS
ouse
0.88
child
0.87
iop
0.82
amn
0.81
orse
0.79
some
0.79
rome
0.77
diapers
0.76
rift
0.75
orne
0.75
Activations Density 0.016%