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

    Neuronpedia

    INDEX
    Explanations

    short phrases or sentences that are formatted as lists

    oai_token-act-pair · gpt-3.5-turbo

    references to list structures and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McAuliffe
    -0.72
     Samar
    -0.70
     carriage
    -0.67
     braking
    -0.66
    Benz
    -0.66
    inea
    -0.66
    coni
    -0.65
    iday
    -0.65
    steen
    -0.64
    ãĥ¡
    -0.64
    POSITIVE LOGITS
     Lists
    0.80
    DragonMagazine
    0.73
     aggregation
    0.73
     lists
    0.72
     curated
    0.71
     "$:/
    0.71
     shelves
    0.71
     widget
    0.71
    ilogy
    0.71
     charts
    0.70
    Act Density 0.568%

    No Known Activations