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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to America and its geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.80
    BIL
    -0.71
     practition
    -0.69
     submar
    -0.68
    olkien
    -0.65
     pione
    -0.65
    ThumbnailImage
    -0.62
    ActionCode
    -0.61
     Soda
    -0.60
     Nikki
    -0.60
    POSITIVE LOGITS
     globe
    0.80
     aisle
    0.79
    annels
    0.72
     borders
    0.71
     seams
    0.71
     continents
    0.71
    amer
    0.70
     corners
    0.67
    erences
    0.67
     distances
    0.67
    Act Density 0.268%

    No Known Activations