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

    Neuronpedia

    INDEX
    Explanations

    references to domestic workers and their roles

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

    household staff and servants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.47
     Participants
    -0.44
    Participating
    -0.41
     Participant
    -0.41
     Participating
    -0.41
    ighters
    -0.39
    Participants
    -0.39
    ighting
    -0.39
     समीक्षक
    -0.39
    Frat
    -0.39
    POSITIVE LOGITS
     servants
    1.11
     housekeeper
    1.04
     servant
    1.00
     maid
    0.98
     maids
    0.97
     butler
    0.91
     nanny
    0.88
     hired
    0.88
     chauffeur
    0.87
     Servants
    0.86
    Act Density 0.048%

    No Known Activations