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

    Neuronpedia

    INDEX
    Explanations

    references to discrimination based on race, religion, and other identity markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     collapses
    -0.70
     tabl
    -0.68
    merce
    -0.65
     Administ
    -0.60
     cheat
    -0.60
    stress
    -0.59
     Finder
    -0.59
    ologue
    -0.58
    cheat
    -0.58
    ••
    -0.57
    POSITIVE LOGITS
     Race
    0.72
    Gender
    0.72
     Gender
    0.71
    Race
    0.68
    loc
    0.67
     gender
    0.67
    ku
    0.67
    alore
    0.64
    imar
    0.64
    lation
    0.64
    Act Density 0.107%

    No Known Activations