INDEX
Explanations
references to military and security forces
New Auto-Interp
Negative Logits
ãģıãģł
-0.18
edla
-0.16
afia
-0.15
aggress
-0.15
ÏĥÏĦÏģο
-0.15
opard
-0.14
æ¾
-0.14
Dữ
-0.14
åģ
-0.14
vui
-0.13
POSITIVE LOGITS
OrCreate
0.15
Anders
0.14
kr
0.14
nad
0.14
Nat
0.14
Christie
0.13
nowrap
0.13
AndView
0.13
Hanson
0.13
آدÙħ
0.13
Activations Density 0.048%