INDEX
Explanations
mentions of clothing items, specifically t-shirts
references to t-shirts and shopping
New Auto-Interp
Negative Logits
ragon
-0.93
Strikes
-0.78
etter
-0.71
agraph
-0.70
interstitial
-0.62
OTH
-0.62
uffs
-0.61
agitation
-0.61
iev
-0.61
untu
-0.60
POSITIVE LOGITS
glers
0.93
andise
0.83
plates
0.79
Boys
0.77
ãĤ¦ãĤ¹
0.76
tee
0.76
Shop
0.76
ging
0.75
Boy
0.75
osphere
0.74
Activations Density 0.020%