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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discrimination and bias based on various characteristics such as race, gender, sexual orientation, and nationality

    oai_token-act-pair · gpt-3.5-turbo

    references to discrimination based on various characteristics such as race, sexual orientation, or disability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eva
    -0.82
    iland
    -0.77
    jet
    -0.75
    cca
    -0.69
    Guard
    -0.67
    MO
    -0.66
    adia
    -0.65
    cember
    -0.64
    NAS
    -0.64
    jan
    -0.64
    POSITIVE LOGITS
     ethnicity
    1.24
     nationality
    1.18
     merit
    1.13
     whether
    1.07
     race
    1.05
     gender
    1.04
     characteristics
    1.03
     geography
    1.02
     demographics
    1.01
     similarity
    1.00
    Act Density 0.245%

    No Known Activations