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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "when" in contexts related to notable events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odu
    -0.17
    oma
    -0.17
    omas
    -0.17
    ÑĶм
    -0.16
    etty
    -0.16
    hm
    -0.15
    hya
    -0.15
    ัà¸ķà¸ĸ
    -0.15
    atk
    -0.15
    point
    -0.15
    POSITIVE LOGITS
    TypeInfo
    0.15
    lush
    0.15
     cool
    0.14
    ãĥ³ãĤ¿
    0.14
     Cone
    0.14
    ryn
    0.14
     Dud
    0.14
    enery
    0.13
     col
    0.13
    Å¡et
    0.13
    Act Density 0.081%

    No Known Activations