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

    Neuronpedia

    INDEX
    Explanations

    terms related to modeling or models, which can refer to various contexts like fashion, technology, or representation

    oai_token-act-pair · gpt-3.5-turbo

    references to models, particularly in contexts related to fashion or representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.96
    ulhu
    -0.85
    usters
    -0.83
    lins
    -0.78
    azar
    -0.76
    ugu
    -0.73
    kefeller
    -0.73
    olulu
    -0.73
    omes
    -0.72
    intendo
    -0.71
    POSITIVE LOGITS
    model
    0.82
     Mayhem
    0.78
     Penal
    0.78
    models
    0.72
    Loader
    0.66
    Upload
    0.66
     photographed
    0.66
     organism
    0.65
    )=(
    0.65
     Models
    0.65
    Act Density 0.017%

    No Known Activations