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

    Neuronpedia

    INDEX
    Explanations

    nationalities of different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or ethnic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Chain
    -0.69
     Chain
    -0.63
    Smith
    -0.63
    scape
    -0.62
    miss
    -0.61
     confirmation
    -0.61
    CHECK
    -0.60
    Virginia
    -0.59
    Leader
    -0.59
    ologically
    -0.59
    POSITIVE LOGITS
    aurus
    1.02
    paces
    1.00
    ugi
    0.89
     who
    0.88
    ourced
    0.81
    ervatives
    0.79
    ktop
    0.78
     stationed
    0.78
    ervative
    0.77
    ouls
    0.77
    Act Density 0.049%

    No Known Activations