INDEX
Explanations
references to gun control issues and policies
New Auto-Interp
Negative Logits
.vo
-0.15
isser
-0.15
oldem
-0.15
ICO
-0.14
aska
-0.14
ounce
-0.14
.uml
-0.14
ulti
-0.13
.fhir
-0.13
seys
-0.13
POSITIVE LOGITS
plus
0.21
PLUS
0.16
lots
0.16
Plus
0.16
new
0.16
plus
0.16
a
0.15
Plus
0.15
another
0.15
fat
0.14
Activations Density 0.051%