INDEX
Explanations
phrases related to clothing items, specifically sleeves
references to sleeves
New Auto-Interp
Negative Logits
Ĩ
-0.94
atana
-0.79
inction
-0.76
ĺħ
-0.75
alty
-0.72
inctions
-0.71
osta
-0.70
vanquished
-0.69
rase
-0.68
ourke
-0.67
POSITIVE LOGITS
sleeve
1.02
bands
0.92
sleeves
0.91
glers
0.89
neck
0.89
cuff
0.80
ength
0.79
ãĥ¯
0.78
ifted
0.78
shirts
0.77
Activations Density 0.024%