INDEX
Explanations
mentions of a particular sports club
references to a specific sports club
New Auto-Interp
Negative Logits
Accessory
-0.88
PLA
-0.80
haar
-0.76
PLA
-0.72
PUT
-0.70
PROV
-0.67
hower
-0.67
OPLE
-0.64
Lenin
-0.63
Whedon
-0.63
POSITIVE LOGITS
houses
1.00
bing
0.87
imore
0.86
bable
0.86
bers
0.84
mates
0.84
clubs
0.82
bish
0.80
crest
0.80
scout
0.78
Activations Density 0.016%