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

    Neuronpedia

    INDEX
    Explanations

    references to nudity

    oai_token-act-pair · gpt-3.5-turbo

    references to nudity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agents
    -0.73
    rier
    -0.72
    riers
    -0.72
    kee
    -0.69
    ãĥ£
    -0.68
    ppa
    -0.68
    CE
    -0.67
    dule
    -0.67
    soType
    -0.67
    enges
    -0.66
    POSITIVE LOGITS
     naked
    0.92
     mole
    0.89
    legged
    0.87
    ness
    0.83
    nesday
    0.77
     Naked
    0.76
    ity
    0.75
     nude
    0.75
    iary
    0.73
    ucing
    0.72
    Act Density 0.019%

    No Known Activations