INDEX
    Explanations

    names starting with Mar

    New Auto-Interp
    Negative Logits
     all
    -0.96
     where
    -0.95
     this
    -0.94
     for
    -0.91
     some
    -0.90
     As
    -0.88
     does
    -0.88
     doesn
    -0.88
     a
    -0.86
     one
    -0.85
    POSITIVE LOGITS
     consommer
    0.99
     teléfonos
    0.94
     Cire
    0.94
     ISC
    0.90
     relojes
    0.89
     Manuela
    0.89
     аккуратно
    0.88
    Recep
    0.88
    fej
    0.88
     trud
    0.88
    Act Density 0.000%

    No Known Activations