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

    Neuronpedia

    INDEX
    Explanations

    specific measurements and dimensions in a document, such as lengths, heights, and screen sizes

    oai_token-act-pair · gpt-3.5-turbo

    measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vi
    -0.72
    vik
    -0.66
    atu
    -0.64
    FUL
    -0.64
    CVE
    -0.64
     behav
    -0.62
     Buckley
    -0.62
     Samar
    -0.61
     Portug
    -0.61
    arie
    -0.61
    POSITIVE LOGITS
    (-
    0.77
    hedral
    0.74
    abytes
    0.74
    cm
    0.73
     magnification
    0.72
    factor
    0.71
    -+
    0.71
    ÏĤ
    0.70
    fold
    0.69
    pixel
    0.69
    Act Density 0.058%

    No Known Activations