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

    Neuronpedia

    INDEX
    Explanations

    names of persons or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heses
    -0.71
    mble
    -0.69
    agne
    -0.65
    idy
    -0.64
    hammad
    -0.62
    hesis
    -0.62
    rieg
    -0.61
     Directors
    -0.59
    hetical
    -0.59
    wig
    -0.58
    POSITIVE LOGITS
    lot
    0.86
    dro
    0.78
    itous
    0.77
    TAIN
    0.77
    dropping
    0.76
    tain
    0.76
    ourn
    0.73
    ols
    0.71
     Oo
    0.71
    hig
    0.70
    Act Density 0.137%

    No Known Activations