INDEX
Explanations
the frequency and occurrence of specific terms related to firearms and their use in various contexts
New Auto-Interp
Negative Logits
klass
-0.15
ãĥ¼ãĥĭ
-0.15
iasi
-0.15
Äįen
-0.15
OF
-0.15
istrovstvÃŃ
-0.14
Som
-0.14
indow
-0.14
atur
-0.14
-framework
-0.14
POSITIVE LOGITS
arkin
0.16
Fcn
0.16
áž
0.15
oki
0.15
544
0.15
izont
0.15
JECTION
0.15
igure
0.15
markup
0.14
/Private
0.14
Activations Density 0.023%