INDEX
Explanations
references to golf and related activities
New Auto-Interp
Negative Logits
phrine
-0.53
droog
-0.50
granate
-0.48
répondit
-0.48
fandom
-0.47
AllowUser
-0.45
basan
-0.44
cency
-0.44
henne
-0.43
kultury
-0.43
POSITIVE LOGITS
golf
1.85
Golf
1.72
Golf
1.69
golfing
1.68
golf
1.66
GOLF
1.64
golfer
1.57
golfers
1.52
GOLF
1.44
ゴルフ
1.14
Activations Density 0.086%