INDEX
Explanations
items of clothing
occurrences of the word "clothes."
New Auto-Interp
Negative Logits
utherford
-0.71
Woodward
-0.69
umar
-0.68
ipolar
-0.68
Kern
-0.67
unanim
-0.67
odcast
-0.66
ĵĺ
-0.64
Iraq
-0.64
ctive
-0.63
POSITIVE LOGITS
pins
1.09
leeve
1.04
clothes
1.02
worn
1.00
clothing
0.96
bag
0.95
puter
0.95
garments
0.92
bags
0.92
trousers
0.91
Activations Density 0.013%