INDEX
    Explanations

    occurrences of the word "von" related to authorship or attribution

    New Auto-Interp
    Negative Logits
    ñana
    -0.15
    ebek
    -0.14
    ategorized
    -0.14
    sob
    -0.14
    ôm
    -0.14
    eam
    -0.14
    oppins
    -0.14
    à¹ģล
    -0.14
     Glob
    -0.14
    /fast
    -0.14
    POSITIVE LOGITS
     hier
    0.17
    446
    0.15
     quer
    0.14
    /ac
    0.14
    316
    0.14
    arel
    0.14
    304
    0.14
    /to
    0.14
     Farrell
    0.14
    ool
    0.14
    Act Density 0.014%

    No Known Activations