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

    Neuronpedia

    INDEX
    Explanations

    descriptions of people and their actions or roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the roles and actions of individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .",
    -0.70
    ifferent
    -0.67
    nikov
    -0.65
    ifference
    -0.64
    .–
    -0.64
     unbeliev
    -0.63
    rary
    -0.62
    urers
    -0.62
    relative
    -0.61
    chwitz
    -0.60
    POSITIVE LOGITS
     presided
    0.73
     Debor
    0.69
     ?)
    0.68
     retiring
    0.68
    ?)
    0.67
    pires
    0.65
     Seas
    0.64
     jailed
    0.64
     sits
    0.63
     overseeing
    0.63
    Act Density 0.326%

    No Known Activations