INDEX
Explanations
references to political parties and affiliations
New Auto-Interp
Negative Logits
æļ
-0.16
complexes
-0.16
arb
-0.15
.contract
-0.15
PIO
-0.14
é«ĺéĢŁ
-0.14
aset
-0.14
Contracts
-0.14
rebel
-0.14
flake
-0.13
POSITIVE LOGITS
party
0.23
parties
0.20
Party
0.20
Movement
0.18
Party
0.18
party
0.18
movement
0.17
PARTY
0.17
spl
0.17
Movement
0.16
Activations Density 0.098%