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

    Neuronpedia

    INDEX
    Explanations

    words related to social stigma and shame

    oai_token-act-pair · gpt-3.5-turbo

    references to stigma and its related concepts, particularly in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apeake
    -0.75
    ramid
    -0.71
    ebus
    -0.68
    plan
    -0.67
    hire
    -0.66
    éĹĺ
    -0.63
    goal
    -0.62
     pickups
    -0.61
    irgin
    -0.61
    artment
    -0.61
    POSITIVE LOGITS
     stigma
    1.15
     stigmat
    0.95
    imaru
    0.85
     Shame
    0.72
    ãħĭ
    0.72
    endered
    0.71
     ostr
    0.69
    ega
    0.67
     prejudice
    0.67
    ovan
    0.66
    Act Density 0.028%

    No Known Activations