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

    Neuronpedia

    INDEX
    Explanations

    references to racial and ethnic identities and their historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    white servants and slaves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.67
    🏾
    -0.62
     africaine
    -0.62
     africains
    -0.61
     African
    -0.57
     africain
    -0.56
    アフリカ
    -0.54
     África
    -0.53
     Afrique
    -0.52
     negroes
    -0.52
    POSITIVE LOGITS
    Aust
    0.41
     MainAxisSize
    0.40
    bora
    0.39
    confirmButton
    0.38
    yntaxException
    0.38
    Dict
    0.38
    IntoConstraints
    0.37
     Bombs
    0.37
     模
    0.37
    bom
    0.36
    Act Density 0.179%

    No Known Activations