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

    names or initials of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Confederation
    -0.61
    Marie
    -0.61
     Nicolas
    -0.60
     COP
    -0.58
    âĶĢâĶĢ
    -0.57
     unic
    -0.56
     Duterte
    -0.54
     Egyptian
    -0.52
     Geh
    -0.52
     Dele
    -0.52
    POSITIVE LOGITS
    ramer
    0.84
    iew
    0.73
    arthed
    0.70
    zinski
    0.69
    ĵĺ
    0.68
    lett
    0.67
    ardy
    0.65
    mire
    0.65
    hement
    0.64
    abwe
    0.63
    Act Density 0.143%

    No Known Activations