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

    Neuronpedia

    INDEX
    Explanations

    dates or numerical values in documents

    oai_token-act-pair · gpt-3.5-turbo

    elements related to structured data presentation or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fml
    -0.72
     Samoa
    -0.63
    uddin
    -0.62
    ãĤ¼
    -0.60
    aterasu
    -0.59
    Benz
    -0.59
    iland
    -0.59
    camp
    -0.59
    ushima
    -0.58
    ãĥ¡
    -0.58
    POSITIVE LOGITS
    hesion
    0.72
    xus
    0.72
    agall
    0.68
    hers
    0.68
    opus
    0.67
    iameter
    0.64
    ciation
    0.64
    ulhu
    0.63
     Generic
    0.62
    otomy
    0.61
    Act Density 0.786%

    No Known Activations