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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enei
    -0.89
    atility
    -0.84
    opard
    -0.80
    heed
    -0.79
    etsk
    -0.79
     compr
    -0.78
    pered
    -0.77
    hene
    -0.76
    ACH
    -0.69
    sylvania
    -0.69
    POSITIVE LOGITS
     Gathering
    0.83
     "$:/
    0.75
     EntityItem
    0.73
     Ny
    0.73
     Advisory
    0.70
     Freder
    0.70
    icle
    0.70
    ãĥ¤
    0.69
     Laur
    0.68
    istic
    0.68
    Act Density 0.016%

    No Known Activations