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

    Neuronpedia

    INDEX
    Explanations

    references to legal or official documents

    oai_token-act-pair · gpt-3.5-turbo

    references to immigration documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    si
    -0.72
    range
    -0.68
    iak
    -0.68
    oise
    -0.66
    rian
    -0.66
    itcher
    -0.65
     Charleston
    -0.64
    alian
    -0.64
     apartheid
    -0.62
    lua
    -0.62
    POSITIVE LOGITS
     papers
    1.21
    peed
    0.93
     Papers
    0.92
     towels
    0.87
    papers
    0.83
    chool
    0.80
    Paper
    0.79
     Journals
    0.77
    ertation
    0.77
    clips
    0.76
    Act Density 0.011%

    No Known Activations