INDEX
    Explanations

    the word "bro" with varying intensities

    the informal term "bro" used in various contexts

    New Auto-Interp
    Negative Logits
    ansas
    -0.85
    rill
    -0.81
    istics
    -0.80
    ertodd
    -0.78
    ition
    -0.77
    ging
    -0.77
    glass
    -0.76
    gment
    -0.75
    riet
    -0.73
    ram
    -0.72
    POSITIVE LOGITS
     tuna
    0.74
    hirt
    0.73
     Tune
    0.66
    heads
    0.64
     Mercury
    0.63
     pitched
    0.63
     Trout
    0.62
     wig
    0.62
     Nero
    0.62
     sax
    0.60
    Act Density 0.069%

    No Known Activations