INDEX
    Explanations

    titles of artistic works and their authors

    New Auto-Interp
    Negative Logits
    ippi
    -0.17
    veau
    -0.15
    gree
    -0.15
    ë§ī
    -0.14
    Ñħов
    -0.14
    quip
    -0.14
    gebn
    -0.14
    orthy
    -0.14
    deaux
    -0.14
    .Sin
    -0.14
    POSITIVE LOGITS
     usage
    0.16
    arp
    0.16
    arpa
    0.15
     folks
    0.15
     Robinson
    0.15
     Transparent
    0.14
    anson
    0.14
     Parad
    0.14
     crime
    0.14
    usage
    0.14
    Act Density 0.116%

    No Known Activations