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

    Neuronpedia

    INDEX
    Explanations

    references to population statistics and demographic trends

    oai_token-act-pair · gpt-3.5-turbo

    references to population statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.82
    href
    -0.79
    vell
    -0.79
    argon
    -0.74
    eryl
    -0.72
    uran
    -0.71
    urn
    -0.70
    eworthy
    -0.68
    rontal
    -0.67
    sbm
    -0.67
    POSITIVE LOGITS
     density
    0.79
     residing
    0.77
    population
    0.77
    atics
    0.76
     centers
    0.74
    wide
    0.73
     inhab
    0.71
     genetics
    0.71
     bases
    0.69
     dwelling
    0.67
    Act Density 0.045%

    No Known Activations