INDEX
Explanations
references to purchasing or shopping items
New Auto-Interp
Negative Logits
igne
-0.15
Curtain
-0.15
thumbs
-0.15
ogle
-0.14
ppe
-0.14
Commonwealth
-0.14
Brill
-0.14
aman
-0.14
crack
-0.14
anel
-0.13
POSITIVE LOGITS
omed
0.16
reau
0.16
imb
0.15
oron
0.15
º«
0.15
purch
0.15
éĢļ
0.15
erton
0.15
éł
0.15
novelty
0.15
Activations Density 0.309%