INDEX
Explanations
phrases indicative of arguments or discussions surrounding gun ownership and legislation
New Auto-Interp
Negative Logits
criptor
-0.16
wu
-0.15
amak
-0.15
_CE
-0.14
CHK
-0.14
ugi
-0.14
ullets
-0.14
acula
-0.14
ilde
-0.13
_specific
-0.13
POSITIVE LOGITS
currently
0.23
except
0.21
presently
0.21
currently
0.20
except
0.20
Currently
0.19
Currently
0.18
缮åīį
0.18
Except
0.17
Except
0.16
Activations Density 0.003%