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

    Neuronpedia

    INDEX
    Explanations

    references to objects or activities related to manual skills or craftsmanship, such as "hand-made," "hand-numbered," or "handling."

    oai_token-act-pair · gpt-3.5-turbo

    references to handmade items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.77
    idian
    -0.74
     Tonight
    -0.73
    vell
    -0.72
     Atmosp
    -0.70
    anus
    -0.69
    oreal
    -0.68
    nces
    -0.66
    actionDate
    -0.65
    ctory
    -0.65
    POSITIVE LOGITS
    maid
    1.17
    bag
    1.17
    picked
    1.13
    crafted
    1.12
    ily
    1.06
    bags
    1.05
    shake
    1.04
    book
    0.97
    books
    0.95
    lers
    0.90
    Act Density 0.037%

    No Known Activations