INDEX
    Explanations

    mentions of book titles and authors

    New Auto-Interp
    Negative Logits
     verd
    -0.15
    ouser
    -0.15
    urm
    -0.15
    .Butter
    -0.15
    stery
    -0.14
    uments
    -0.14
    ilestone
    -0.14
    ully
    -0.14
    nown
    -0.13
    alley
    -0.13
    POSITIVE LOGITS
     meis
    0.15
    eyer
    0.15
    648
    0.14
    -series
    0.14
    zzo
    0.14
    Mods
    0.14
     IMPLEMENT
    0.14
     Odds
    0.14
    ð
    0.14
    ialis
    0.13
    Act Density 0.475%

    No Known Activations