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

    Neuronpedia

    INDEX
    Explanations

    references to stereotypes, particularly those related to Native Americans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.44
     bağlantılar
    -0.40
    RTLU
    -0.39
    дарю
    -0.38
    \{\\
    -0.38
    digkeit
    -0.36
    loài
    -0.36
     pleaſure
    -0.36
    Jereo
    -0.36
     pray
    -0.35
    POSITIVE LOGITS
     stereotypes
    1.61
     misconceptions
    1.52
     precon
    1.45
     stereotype
    1.43
     misconception
    1.34
     prejudices
    1.30
     myths
    1.29
     perceptions
    1.27
     stigma
    1.23
     perception
    1.20
    Act Density 0.637%

    No Known Activations