INDEX
Explanations
terms related to board games
mentions of board games
New Auto-Interp
Negative Logits
Hoover
-0.85
icity
-0.82
olon
-0.72
plural
-0.69
uality
-0.68
ibility
-0.65
Brigham
-0.65
Flask
-0.64
Leone
-0.63
Revel
-0.63
POSITIVE LOGITS
walk
1.37
board
1.18
wal
1.09
meal
1.09
gaming
0.99
rooms
0.96
chair
0.96
room
0.95
ridges
0.94
game
0.94
Activations Density 0.021%