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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Andrews" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozyg
    -0.81
    atorial
    -0.80
    orescent
    -0.78
    itably
    -0.78
    acts
    -0.75
    ounty
    -0.75
    ately
    -0.73
    crime
    -0.71
    onest
    -0.71
     redistributed
    -0.70
    POSITIVE LOGITS
     Andrews
    1.13
    shire
    0.96
    endor
    0.89
    sburg
    0.87
     Lans
    0.85
    issance
    0.81
    boro
    0.75
     AFB
    0.74
    hurst
    0.72
    mort
    0.71
    Act Density 0.006%

    No Known Activations