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

    Neuronpedia

    INDEX
    Explanations

    words related to intelligence, specifically IQ scores

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence and IQ

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.75
    coni
    -0.71
    bare
    -0.69
    Joined
    -0.68
     Soda
    -0.67
    woman
    -0.67
    than
    -0.64
    comed
    -0.63
    advertisement
    -0.63
    ãĤĤ
    -0.63
    POSITIVE LOGITS
     IQ
    1.02
    IQ
    0.96
     quot
    0.89
    iencies
    0.85
    atsu
    0.82
     score
    0.82
     enrichment
    0.82
     percentile
    0.78
     scores
    0.78
    orsi
    0.77
    Act Density 0.026%

    No Known Activations