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

    Neuronpedia

    INDEX
    Explanations

    phrases related to additional information or content that are distinct from the main text

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or categories that are labeled as "other"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffee
    -0.70
    vet
    -0.66
    itan
    -0.65
    orney
    -0.63
     1915
    -0.62
     2024
    -0.61
    ARS
    -0.61
     ç¥ŀ
    -0.61
     piety
    -0.60
     moment
    -0.58
    POSITIVE LOGITS
    worldly
    1.57
    wise
    1.06
    quickShipAvailable
    1.03
    etheless
    0.90
    swer
    0.90
     notable
    0.80
    world
    0.79
     Sources
    0.79
    parts
    0.77
    body
    0.77
    Act Density 0.056%

    No Known Activations