INDEX
Explanations
references to types of clothing, especially jackets
references to jackets in various contexts
New Auto-Interp
Negative Logits
rians
-0.73
MacArthur
-0.71
minist
-0.70
agram
-0.65
mission
-0.65
mony
-0.64
axis
-0.63
ADRA
-0.63
ASY
-0.62
rian
-0.61
POSITIVE LOGITS
jacket
1.22
jackets
1.20
Jacket
1.13
sleeves
1.08
sleeve
1.02
coats
0.92
worn
0.86
Jackets
0.85
racks
0.81
coat
0.80
Activations Density 0.017%