INDEX
    Explanations

    titles of books, movies, or music albums

    New Auto-Interp
    Negative Logits
    ĻĤ
    -1.01
    Ͻ
    -0.76
    ¸
    -0.73
    İĭ
    -0.73
    onite
    -0.70
    ¾
    -0.68
    etheless
    -0.66
    ailing
    -0.66
    stant
    -0.64
    ¿
    -0.64
    POSITIVE LOGITS
    /"
    1.29
     moniker
    0.79
     aka
    0.79
    >>\
    0.73
     ("
    0.72
    SPONSORED
    0.71
    aneers
    0.69
    Minecraft
    0.69
     motto
    0.69
     ["
    0.68
    Act Density 0.087%

    No Known Activations