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

    Neuronpedia

    INDEX
    Explanations

    phrases involving payments or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to payments and expenses, particularly in the context of finances and taxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -1.03
    çİĭ
    -0.71
    itivity
    -0.70
    iqueness
    -0.69
    successful
    -0.68
    failed
    -0.67
    rame
    -0.67
    Ö¼
    -0.66
    apons
    -0.65
     Gutenberg
    -0.64
    POSITIVE LOGITS
     dues
    1.23
     taxes
    1.17
     dividends
    1.13
     ransom
    1.05
     fees
    1.05
     premiums
    1.04
     homage
    1.03
     royalties
    1.03
     heed
    1.02
     bribes
    0.99
    Act Density 0.130%

    No Known Activations