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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.82
    omething
    -0.79
    ements
    -0.76
    initialized
    -0.75
    ktop
    -0.71
    inates
    -0.71
    eu
    -0.71
    roups
    -0.70
    agers
    -0.69
    atem
    -0.68
    POSITIVE LOGITS
     Slater
    0.79
     Clarke
    0.76
     Porter
    0.74
     MacArthur
    0.73
     Cyrus
    0.72
     Rae
    0.71
    quist
    0.71
     Shepherd
    0.70
     Coulter
    0.69
     Baldwin
    0.69
    Act Density 0.072%

    No Known Activations