INDEX
    Explanations

    the mention of the word "source" in various contexts

    references to "source" material or citations

    New Auto-Interp
    Negative Logits
    aeper
    -0.92
    achine
    -0.79
    Ħ¢
    -0.77
    awks
    -0.73
    ipop
    -0.73
    ategory
    -0.73
    jriwal
    -0.72
    nesday
    -0.72
    PDATE
    -0.71
    wagen
    -0.70
    POSITIVE LOGITS
    Fed
    0.95
    books
    0.93
    finding
    0.88
    book
    0.86
    source
    0.83
     sources
    0.82
     source
    0.81
    forge
    0.80
    aments
    0.78
    finder
    0.78
    Act Density 0.033%

    No Known Activations