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

    Neuronpedia

    INDEX
    Explanations

    references to numerical percentages and figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to proportions and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itialized
    -0.73
    Synopsis
    -0.71
    hur
    -0.70
    book
    -0.65
     Tours
    -0.65
    weather
    -0.64
     scheduling
    -0.64
     sche
    -0.63
    seq
    -0.62
    travel
    -0.62
    POSITIVE LOGITS
    Percent
    1.33
    %;
    1.18
     percentage
    1.18
    percent
    1.16
    %,
    1.15
     percentages
    1.14
    %).
    1.12
    %.
    1.12
    %-
    1.12
     majorities
    1.11
    Act Density 0.289%

    No Known Activations