INDEX
Explanations
mentions of wrist-related objects or actions
references to body parts, particularly the wrist
New Auto-Interp
Negative Logits
xual
-0.87
eming
-0.68
issy
-0.68
NESS
-0.66
actionDate
-0.63
REDACTED
-0.62
Newsweek
-0.62
EXP
-0.62
due
-0.61
UES
-0.61
POSITIVE LOGITS
bands
1.22
strap
1.16
cuff
1.07
strap
1.02
watch
1.01
wrist
0.97
band
0.96
straps
0.94
links
0.93
locks
0.89
Activations Density 0.007%