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

    Neuronpedia

    INDEX
    Explanations

    medical and health-related terms, particularly those related to mental health and medications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mental health and disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    books
    -0.71
    TING
    -0.70
    erness
    -0.70
     Hole
    -0.70
    book
    -0.66
     Pixie
    -0.65
    htaking
    -0.65
    packages
    -0.64
    soDeliveryDate
    -0.64
    sheet
    -0.63
    POSITIVE LOGITS
    ological
    0.89
    rison
    0.88
    relation
    0.84
    andom
    0.83
    ologists
    0.83
    ategory
    0.81
    ased
    0.81
    ally
    0.79
    aceutical
    0.79
    pheus
    0.77
    Act Density 0.024%

    No Known Activations