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

    Neuronpedia

    INDEX
    Explanations

    references to hands or activities related to hands

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "hand" with varying contexts related to craft or skill

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ËĪ
    -0.76
    ashtra
    -0.74
    actionDate
    -0.71
    é¾
    -0.68
    ĵĺ
    -0.68
    ļéĨĴ
    -0.66
     RAND
    -0.66
     Atmosp
    -0.65
    anus
    -0.65
     recomm
    -0.64
    POSITIVE LOGITS
    crafted
    1.24
    maid
    1.20
    picked
    1.17
    ily
    1.14
    bag
    1.12
    shake
    1.11
    bags
    1.10
    book
    1.02
    lers
    1.01
    books
    0.98
    Act Density 0.036%

    No Known Activations