INDEX
Explanations
words related to a gym or physical fitness activities
references to gyms
New Auto-Interp
Negative Logits
IBLE
-0.79
Strait
-0.74
ICT
-0.70
SPONSORED
-0.65
theless
-0.62
ocument
-0.62
OVER
-0.62
alez
-0.59
ictional
-0.59
interstellar
-0.59
POSITIVE LOGITS
nas
1.76
rats
0.87
tub
0.83
mers
0.81
nos
0.81
rition
0.81
bell
0.79
floor
0.79
sters
0.79
lain
0.78
Activations Density 0.018%