INDEX
    Explanations

    references to commercial establishments and their characteristics

    New Auto-Interp
    Negative Logits
     follando
    -0.22
    FromClass
    -0.18
     modne
    -0.17
    idente
    -0.17
     analsex
    -0.16
     rumpe
    -0.16
     nakne
    -0.15
    cobra
    -0.15
     odense
    -0.15
     posição
    -0.15
    POSITIVE LOGITS
     recipient
    0.18
     formas
    0.18
     elementos
    0.17
     ingredient
    0.17
     los
    0.17
     otros
    0.17
     tipos
    0.16
     mét
    0.16
     grandes
    0.16
     pá
    0.16
    Act Density 0.067%

    No Known Activations