INDEX
Explanations
mentions of locations, particularly the city of Minneapolis
references to the city of Minneapolis
New Auto-Interp
Negative Logits
redo
-0.85
Scotia
-0.72
ning
-0.71
Penet
-0.70
ICAN
-0.67
uchin
-0.67
oiler
-0.63
Tags
-0.63
APE
-0.62
binary
-0.61
POSITIVE LOGITS
ĸļ
0.97
kens
0.90
borough
0.89
neapolis
0.85
paces
0.84
erville
0.83
hip
0.82
pace
0.80
olulu
0.79
omes
0.78
Activations Density 0.051%