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

    Neuronpedia

    INDEX
    Explanations

    references to disability-related inquiries and the legal implications under the ADA (Americans with Disabilities Act)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.15
    abase
    -0.15
    Wnd
    -0.14
    allet
    -0.14
    abilia
    -0.14
    à¤Ĥधन
    -0.14
    lendir
    -0.14
    hek
    -0.14
    åºľ
    -0.14
    ç¨
    -0.14
    POSITIVE LOGITS
     discrimination
    0.24
     Discrim
    0.21
     protected
    0.21
     discrim
    0.20
     discriminator
    0.20
    Protected
    0.19
     discriminatory
    0.19
    protected
    0.19
     Protected
    0.17
    HR
    0.17
    Act Density 0.056%

    No Known Activations