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

    Neuronpedia

    INDEX
    Explanations

    numbers and characters in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and terms related to health conditions or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.90
    NetMessage
    -0.88
    isters
    -0.80
    icter
    -0.80
    perty
    -0.79
    mits
    -0.79
    ippi
    -0.76
    ysical
    -0.75
    oning
    -0.75
    istine
    -0.72
    POSITIVE LOGITS
    er
    0.75
    ness
    0.74
    ty
    0.72
    ative
    0.72
    ribution
    0.71
    ãĤª
    0.70
    rition
    0.70
    atively
    0.68
    culosis
    0.68
    rage
    0.68
    Act Density 0.043%

    No Known Activations