INDEX
Explanations
references to facial hair styling
references to facial hair, specifically beards and mustaches
New Auto-Interp
Negative Logits
VD
-0.77
GOODMAN
-0.72
ramid
-0.72
phis
-0.72
EMS
-0.72
PsyNetMessage
-0.68
Vaj
-0.66
izable
-0.62
MN
-0.62
awaru
-0.62
POSITIVE LOGITS
beard
1.16
beard
1.12
mustache
0.99
shaving
0.89
shaved
0.86
Beard
0.86
shave
0.85
rette
0.84
trimmed
0.81
hairy
0.73
Activations Density 0.019%