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

    Neuronpedia

    INDEX
    Explanations

    numerical references and metrics related to technology and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥªãĥ¼ãĤº
    -0.17
    oui
    -0.15
    ÑĢади
    -0.15
    tember
    -0.15
    fax
    -0.15
    orate
    -0.15
    átis
    -0.14
     gá»įn
    -0.14
    _checks
    -0.14
    ONTAL
    -0.14
    POSITIVE LOGITS
    s
    0.15
    ï¸ı
    0.15
     Hao
    0.14
    ez
    0.14
    cio
    0.14
    ìľ¨
    0.14
     rue
    0.14
    itmap
    0.14
    ãģ³
    0.13
    kova
    0.13
    Act Density 0.111%

    No Known Activations