INDEX
    Explanations

    Quotation marks

    New Auto-Interp
    Negative Logits
     Principles
    -0.08
    -0.08
     principles
    -0.08
     Ath
    -0.07
     Ernst
    -0.07
     Abel
    -0.07
     Southwestern
    -0.07
    -oh
    -0.07
     ann
    -0.07
    Entire
    -0.07
    POSITIVE LOGITS
     loja
    0.08
    atura
    0.08
    0.08
    quart
    0.08
    industry
    0.08
     Wirtschaft
    0.08
    itoa
    0.08
    bounce
    0.07
    phone
    0.07
    0.07
    Act Density 0.005%

    No Known Activations