INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    uador
    -0.76
    =-=-
    -0.73
    PsyNetMessage
    -0.72
    ilities
    -0.72
    cffffcc
    -0.71
    rolet
    -0.71
    vre
    -0.71
    =-=-=-=-
    -0.69
    apist
    -0.67
    BIL
    -0.67
    POSITIVE LOGITS
    beard
    1.14
    berry
    1.10
    stone
    1.05
    heads
    1.03
    bird
    1.02
    horse
    1.01
    haired
    0.99
    headed
    0.99
    hawk
    0.98
    fish
    0.97
    Act Density 3.003%

    No Known Activations