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

    Neuronpedia

    INDEX
    Explanations

    personal names in business contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of CEOs or high-level executives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gettable
    -0.70
     wounding
    -0.67
     regress
    -0.66
    CVE
    -0.64
    worldly
    -0.64
     feral
    -0.63
    shapeshifter
    -0.62
     heroine
    -0.62
     unarmed
    -0.61
    tackle
    -0.61
    POSITIVE LOGITS
     Sales
    0.96
     Investment
    0.92
    CEO
    0.90
     Holdings
    0.87
     Goldman
    0.87
     Brands
    0.86
     IPO
    0.84
     Bid
    0.83
     Seller
    0.82
     Investments
    0.82
    Act Density 0.197%

    No Known Activations