INDEX
Explanations
terms related to various republics and states, particularly in a historical context
New Auto-Interp
Negative Logits
inflow
-0.40
writings
-0.40
ANKS
-0.37
InputChange
-0.36
tortured
-0.36
inspire
-0.36
Romanian
-0.35
Afrikaans
-0.35
Canadian
-0.35
}^{[-0.35
POSITIVE LOGITS
Republic
0.91
republic
0.83
empire
0.81
Republics
0.79
Republic
0.79
republics
0.78
REPUBLIC
0.76
kingdom
0.76
kingdom
0.75
república
0.73
Activations Density 0.448%