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

    Neuronpedia

    INDEX
    Explanations

    mentions of human anatomy, specifically brains and heads

    oai_token-act-pair · gpt-3.5-turbo

    references to the brain and mental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Prosecut
    -0.65
    ression
    -0.64
    ECH
    -0.62
    INA
    -0.62
    ressive
    -0.61
    ee
    -0.61
    card
    -0.61
    rav
    -0.61
    onomy
    -0.60
    Delivery
    -0.60
    POSITIVE LOGITS
    chool
    1.54
    mith
    1.45
    paces
    1.41
    pring
    1.38
    pace
    1.33
    creen
    1.32
    cale
    1.30
    ystem
    1.27
    hips
    1.25
    hare
    1.19
    Act Density 0.088%

    No Known Activations