INDEX
Explanations
phrases indicating corporate influence and control over public resources
New Auto-Interp
Negative Logits
jang
-0.15
мÑĸн
-0.15
iris
-0.14
رد
-0.14
rud
-0.14
imei
-0.13
DK
-0.13
erno
-0.13
setattr
-0.13
esy
-0.13
POSITIVE LOGITS
corporations
0.39
corporate
0.35
corporation
0.32
corpor
0.31
Corporate
0.30
Corpor
0.30
profits
0.30
Wall
0.30
profit
0.29
CORPOR
0.27
Activations Density 0.673%