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

    Neuronpedia

    INDEX
    Explanations

    references to population sizes

    oai_token-act-pair · gpt-3.5-turbo

    references to populations and demographic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.86
    vell
    -0.83
    uran
    -0.76
    href
    -0.76
    ĪĴ
    -0.74
    eworthy
    -0.71
    argon
    -0.70
    eryl
    -0.70
    rament
    -0.69
    wcsstore
    -0.69
    POSITIVE LOGITS
     density
    0.83
     residing
    0.78
     centers
    0.77
    population
    0.77
     population
    0.75
    wide
    0.73
     bases
    0.73
    atics
    0.72
     inhab
    0.72
    Population
    0.70
    Act Density 0.031%

    No Known Activations