INDEX
Explanations
mentions of specific American presidents
references to a specific individual identified as "President."
New Auto-Interp
Negative Logits
overload
-0.71
filler
-0.70
subdivision
-0.68
neutron
-0.68
Bulgarian
-0.67
reproduction
-0.67
JPEG
-0.65
scrim
-0.64
utilization
-0.64
capacitor
-0.63
POSITIVE LOGITS
realDonaldTrump
1.22
Jr
1.04
cffffcc
0.97
shall
0.91
issance
0.90
ï¸ı
0.86
ï
0.84
care
0.82
ðŁ
0.82
tre
0.80
Activations Density 0.152%