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

    Neuronpedia

    INDEX
    Explanations

    ideas and beliefs that are debunked or challenged, particularly surrounding societal norms and stereotypes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    emouth
    -0.68
    ktop
    -0.66
    Interstitial
    -0.65
    ients
    -0.62
    orneys
    -0.62
    artney
    -0.62
     appointments
    -0.61
     POLIT
    -0.61
    ×ķ
    -0.60
    foreseen
    -0.60
    POSITIVE LOGITS
    icist
    1.07
    busters
    0.96
    arily
    0.94
    ril
    0.94
    olog
    0.90
    telling
    0.88
    mong
    0.88
    Myth
    0.88
    ologies
    0.88
    lore
    0.84
    Act Density 0.111%

    No Known Activations