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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating payment or consequences related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.87
    ãĤ¼ãĤ¦ãĤ¹
    -0.86
    fy
    -0.74
    aiman
    -0.72
    iverpool
    -0.71
    ierre
    -0.71
    ullivan
    -0.68
    Shape
    -0.68
    apons
    -0.68
    endif
    -0.68
    POSITIVE LOGITS
     dues
    1.21
     ransom
    1.14
     taxes
    1.06
     bills
    1.05
     dearly
    1.03
     dividends
    1.02
     royalties
    1.00
     debts
    0.98
     tuition
    0.96
     salaries
    0.96
    Act Density 0.036%

    No Known Activations