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

    Neuronpedia

    INDEX
    Explanations

    references to monetary values or salaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ure
    -0.17
    rix
    -0.17
    oly
    -0.16
    ÏħÏĥ
    -0.15
    سÙĨ
    -0.15
    íĮĮ
    -0.15
    ri
    -0.15
     autoload
    -0.14
    еÑĢеж
    -0.14
    rint
    -0.14
    POSITIVE LOGITS
    anus
    0.18
    letcher
    0.17
    cola
    0.16
    apolis
    0.16
    erver
    0.15
    stown
    0.15
    arges
    0.15
    idel
    0.15
    ichten
    0.14
    ingleton
    0.14
    Act Density 0.047%

    No Known Activations