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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those related to individuals mentioned in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abor
    -0.78
    arat
    -0.76
    paio
    -0.73
    cular
    -0.64
    assian
    -0.64
    rolog
    -0.64
    rology
    -0.62
    cules
    -0.62
    eday
    -0.62
     marathon
    -0.62
    POSITIVE LOGITS
    ع
    0.78
    utive
    0.74
     Jarrett
    0.74
    ENCE
    0.73
    mint
    0.73
    shire
    0.72
     Rudd
    0.71
     Tracy
    0.70
     McKenzie
    0.69
    issa
    0.67
    Act Density 0.081%

    No Known Activations