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

    Neuronpedia

    INDEX
    Explanations

    instances of stereotypes, particularly those related to Native Americans and references to Columbus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     invokingState
    -0.73
    RenderAtEndOf
    -0.71
     myſelf
    -0.68
     menik
    -0.68
     pectoral
    -0.65
    SharedCtor
    -0.65
     kaarangay
    -0.63
     متعلقه
    -0.63
     ivelany
    -0.63
    unpublished
    -0.63
    POSITIVE LOGITS
     stereotype
    0.90
     stereotypes
    0.81
     stereotyp
    0.74
     stereotypical
    0.73
     Stere
    0.62
    Stere
    0.60
     stere
    0.54
     character
    0.52
    stere
    0.52
     porta
    0.50
    Act Density 0.234%

    No Known Activations