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

    Neuronpedia

    INDEX
    Explanations

    terms related to data storage or processing

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "client."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.85
    udeb
    -0.81
    head
    -0.75
    brace
    -0.71
    MAR
    -0.71
    isSpecialOrderable
    -0.69
    olkien
    -0.68
    pin
    -0.68
    soDeliveryDate
    -0.68
    UNCH
    -0.68
    POSITIVE LOGITS
    ial
    1.24
    eer
    0.92
    ially
    0.91
    ient
    0.86
    ele
    0.83
    iation
    0.82
    e
    0.82
    ean
    0.79
    aily
    0.79
    edly
    0.79
    Act Density 0.057%

    No Known Activations