Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to reckless behavior or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.97
    ĸļ
    -0.86
    ophon
    -0.86
    yrinth
    -0.80
    olithic
    -0.78
    rose
    -0.77
    orthy
    -0.77
    emis
    -0.75
    rooms
    -0.73
    anooga
    -0.72
    POSITIVE LOGITS
     abandon
    0.93
     err
    0.93
     manslaughter
    0.92
     careless
    0.91
     endanger
    0.90
     reckless
    0.90
     behaviour
    0.87
     disregard
    0.86
     irresponsible
    0.85
     behavior
    0.83
    Act Density 0.059%

    No Known Activations