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

    Neuronpedia

    INDEX
    Explanations

    percentage values in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and percentages in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     organising
    -1.04
    BBC
    -0.90
     Whilst
    -0.83
     travelling
    -0.82
     Seym
    -0.79
    aviour
    -0.77
     Nasa
    -0.77
     recognised
    -0.76
     Newcastle
    -0.76
     £
    -0.75
    POSITIVE LOGITS
     percent
    1.97
    percent
    1.45
    %
    1.25
    %,
    1.25
    %;
    1.24
     percentile
    1.23
     percentage
    1.21
     Percent
    1.19
    %.
    1.16
    %)
    1.11
    Act Density 0.071%

    No Known Activations