INDEX
Explanations
references to an individual named "Brad."
the name "Brad" in various contexts
New Auto-Interp
Negative Logits
ĨĴ
-0.72
derog
-0.70
duty
-0.69
tale
-0.68
subsistence
-0.66
VALUE
-0.65
merce
-0.64
wiret
-0.63
spect
-0.62
UME
-0.62
POSITIVE LOGITS
Brad
1.21
enton
1.08
Pitt
1.06
shaw
1.04
iago
0.90
Brad
0.89
bury
0.85
ford
0.81
imir
0.81
bourne
0.80
Activations Density 0.008%