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

    Neuronpedia

    INDEX
    Explanations

    references to population statistics and growth

    oai_token-act-pair · gpt-3.5-turbo

    references to population statistics and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.79
    argon
    -0.74
    eryl
    -0.72
    ĪĴ
    -0.71
    sbm
    -0.71
    pire
    -0.71
    uran
    -0.71
    vell
    -0.70
    rontal
    -0.70
    rah
    -0.69
    POSITIVE LOGITS
     residing
    0.81
    atics
    0.81
     density
    0.79
    wide
    0.79
    population
    0.78
     centers
    0.72
     inhab
    0.71
     born
    0.70
     bases
    0.69
     attributable
    0.68
    Act Density 0.083%

    No Known Activations