INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     vscode
    -0.81
    WriteBarrier
    -0.67
    usermodel
    -0.64
    github
    -0.63
    SpringRunner
    -0.62
    setContentType
    -0.62
     CanadaChoose
    -0.61
    maxY
    -0.60
     BorderRadius
    -0.60
     AppCompat
    -0.58
    POSITIVE LOGITS
     Evita
    0.76
     Nadine
    0.68
     Duma
    0.63
    Packard
    0.63
    adena
    0.62
    localhost
    0.61
    PhysRevLett
    0.61
     surtout
    0.60
    ;-)
    0.60
    ++];
    0.59
    Act Density 0.037%

    No Known Activations