INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Voter
    0.48
    0.46
     CCR
    0.42
     voter
    0.41
     politics
    0.40
    modal
    0.40
     modal
    0.39
     Taxes
    0.39
     Modal
    0.38
    Politics
    0.38
    POSITIVE LOGITS
     soap
    3.73
     Soap
    3.39
    Soap
    3.28
     soaps
    3.19
    soap
    3.13
     SOAP
    2.92
     soapy
    2.78
     sapon
    2.20
    2.20
     साब
    2.19
    Act Density 0.016%

    No Known Activations