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

    Neuronpedia

    INDEX
    Explanations

    references to actions or objects related to the concept of 'hand'

    oai_token-act-pair · gpt-3.5-turbo

    the word "hand" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vell
    -0.77
    ashtra
    -0.77
     Tonight
    -0.73
     RAND
    -0.72
     Neigh
    -0.69
    nces
    -0.69
    uary
    -0.69
     Atmosp
    -0.68
     Bravo
    -0.68
    onential
    -0.67
    POSITIVE LOGITS
    maid
    1.26
    bag
    1.09
    picked
    1.05
    crafted
    0.96
    hand
    0.95
    shake
    0.93
    bra
    0.90
    bags
    0.87
    books
    0.86
    book
    0.85
    Act Density 0.025%

    No Known Activations