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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing the word "dudes"

    oai_token-act-pair · gpt-3.5-turbo

    references to male peers or friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rall
    -0.75
    idate
    -0.75
    TPPStreamerBot
    -0.72
    ifax
    -0.72
    apego
    -0.71
    enko
    -0.70
    pent
    -0.69
    entity
    -0.69
    icipated
    -0.68
    arine
    -0.68
    POSITIVE LOGITS
     jeans
    0.89
     buddies
    0.85
    holes
    0.84
     pics
    0.79
     buddy
    0.79
     wink
    0.77
    ECA
    0.73
    nesday
    0.72
     haircut
    0.71
     darn
    0.71
    Act Density 0.083%

    No Known Activations