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

    Neuronpedia

    INDEX
    Explanations

    mentions of manual or physical actions involving hands

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "hand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.80
    vell
    -0.78
    ļéĨĴ
    -0.73
     Atmosp
    -0.73
     Neigh
    -0.70
    uary
    -0.70
    nces
    -0.69
    idian
    -0.69
     RAND
    -0.68
     Tonight
    -0.68
    POSITIVE LOGITS
    maid
    1.17
    bag
    1.12
    picked
    1.10
    crafted
    1.07
    bags
    0.98
    shake
    0.96
    hand
    0.94
    books
    0.92
    book
    0.91
    ily
    0.88
    Act Density 0.033%

    No Known Activations