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

    Neuronpedia

    INDEX
    Explanations

    keywords related to antisemitism

    oai_token-act-pair · gpt-3.5-turbo

    references to antisemitism and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    woods
    -0.73
    NAS
    -0.65
    aver
    -0.65
    abee
    -0.64
    avez
    -0.64
     Wiggins
    -0.62
    come
    -0.62
    OWER
    -0.61
    packing
    -0.60
    ateur
    -0.60
    POSITIVE LOGITS
     slurs
    0.98
    Semitism
    0.91
    ophobic
    0.91
    Semitic
    0.87
    ophobia
    0.82
     prejudice
    0.80
     tropes
    0.73
    sylv
    0.72
    itism
    0.72
     tendencies
    0.71
    Act Density 0.014%

    No Known Activations