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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a grouping or quantity, particularly those using "or" followed by numbers or more

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.17
    bourg
    -0.16
    /info
    -0.15
    isms
    -0.15
     Politics
    -0.15
    ä¸Ģ个人
    -0.15
    edia
    -0.14
    ADED
    -0.14
    idge
    -0.14
    agy
    -0.14
    POSITIVE LOGITS
    asje
    0.15
    (strtolower
    0.14
    cob
    0.14
     Fay
    0.14
    :UITableView
    0.14
    clar
    0.14
    apel
    0.14
    azon
    0.13
    åįı
    0.13
     notification
    0.13
    Act Density 0.022%

    No Known Activations