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

    Neuronpedia

    INDEX
    Explanations

    concepts related to racial discrimination and privilege

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¿
    -0.17
    esy
    -0.15
    anoi
    -0.15
    üy
    -0.15
    STYPE
    -0.14
    ÃĴ
    -0.14
    ائÙĬ
    -0.13
    ;element
    -0.13
    898
    -0.13
    igin
    -0.13
    POSITIVE LOGITS
     systems
    0.29
     structural
    0.28
     patri
    0.28
     privilege
    0.27
     Patri
    0.27
     systemic
    0.26
    systems
    0.25
     Systems
    0.25
     Structural
    0.25
     structures
    0.24
    Act Density 0.352%

    No Known Activations