INDEX
    Explanations

    controversial

    New Auto-Interp
    Negative Logits
     polymer
    -0.07
     focus
    -0.07
    -Up
    -0.06
     Electro
    -0.06
    around
    -0.06
     saldırı
    -0.06
    	gbc
    -0.06
    .Tween
    -0.06
     thriving
    -0.05
     Demo
    -0.05
    POSITIVE LOGITS
     controversial
    0.10
     divisive
    0.07
    alarına
    0.07
    EF
    0.07
     opin
    0.07
     xb
    0.07
     unpopular
    0.06
    0.06
    .invalid
    0.06
    EMP
    0.06
    Act Density 0.020%

    No Known Activations