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

    Neuronpedia

    INDEX
    Explanations

    terms related to being on the edge or being of secondary importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of marginalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynthesis
    -0.75
    orld
    -0.73
    aternity
    -0.72
    uden
    -0.72
    IVERS
    -0.69
    ILLE
    -0.68
    ullivan
    -0.68
    velt
    -0.68
     largeDownload
    -0.66
    worthiness
    -0.65
    POSITIVE LOGITS
    ised
    1.09
    ized
    0.94
    ization
    0.92
    iary
    0.83
    ities
    0.82
    izes
    0.82
    aneously
    0.81
    iae
    0.80
     marginal
    0.80
    iated
    0.78
    Act Density 0.019%

    No Known Activations