INDEX
Explanations
mentions of the Olympic Games
mentions of the Olympic Games
New Auto-Interp
Negative Logits
lessly
-0.77
erd
-0.75
eric
-0.74
arial
-0.74
erence
-0.73
roid
-0.72
othal
-0.68
peror
-0.67
Desktop
-0.67
stocks
-0.67
POSITIVE LOGITS
medal
1.00
Athlet
0.97
medals
0.94
Games
0.90
athletes
0.90
Torch
0.90
lymp
0.89
Olympic
0.88
Stadium
0.87
Medal
0.85
Activations Density 0.025%