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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manufact
    -0.67
    expensive
    -0.62
     Hulu
    -0.61
     uncons
    -0.58
     Clarkson
    -0.58
    lished
    -0.58
    etitive
    -0.57
    pite
    -0.57
    efe
    -0.56
    iferation
    -0.55
    POSITIVE LOGITS
     Oaks
    0.65
    ukong
    0.64
    cients
    0.64
    zon
    0.63
     Tags
    0.61
     Edwin
    0.59
    xit
    0.59
     Trace
    0.58
    enum
    0.58
    IE
    0.57
    Act Density 0.778%

    No Known Activations