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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly last names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erer
    -0.81
    rosse
    -0.76
    former
    -0.73
    oise
    -0.73
    erers
    -0.73
     Clo
    -0.73
    itia
    -0.73
    ered
    -0.70
    ories
    -0.70
    eur
    -0.70
    POSITIVE LOGITS
    nces
    1.09
    vernment
    1.06
    manship
    0.96
    haw
    0.91
    olor
    0.82
    ammy
    0.81
    veyard
    0.76
    ciplinary
    0.73
    reath
    0.72
    externalActionCode
    0.72
    Act Density 0.014%

    No Known Activations