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

    Neuronpedia

    INDEX
    Explanations

    references to domestic workers, particularly maids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡ov
    -0.16
    iesen
    -0.15
    tics
    -0.15
    yles
    -0.15
    715
    -0.14
    ستÙħ
    -0.14
    VERR
    -0.13
    494
    -0.13
    ká
    -0.13
    431
    -0.13
    POSITIVE LOGITS
    enance
    0.19
    óst
    0.15
     Fah
    0.15
    å£
    0.15
    imoto
    0.15
    ]='
    0.14
    zan
    0.14
    éŀ
    0.14
    _locals
    0.13
    roat
    0.13
    Act Density 0.001%

    No Known Activations