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

    Neuronpedia

    INDEX
    Explanations

    specific timestamps or numerical data in structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elow
    -0.15
    erson
    -0.15
    ãģ¬
    -0.14
     Ole
    -0.14
    ventus
    -0.14
    mez
    -0.13
     Lam
    -0.13
     Inf
    -0.13
     Cart
    -0.13
    dal
    -0.13
    POSITIVE LOGITS
    oÅĽci
    0.17
    ียà¸Ļ
    0.16
    ARGER
    0.14
    หมà¸Ķ
    0.14
    hea
    0.14
    ãĥ¼ãĥª
    0.14
     nackte
    0.14
    xCD
    0.13
    uales
    0.13
    buz
    0.13
    Act Density 0.293%

    No Known Activations