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

    Neuronpedia

    INDEX
    Explanations

    markup tags and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -1.30
     autorytatywna
    -1.29
    ſelf
    -1.23
    ſelves
    -1.22
     pleaſure
    -1.19
     myſelf
    -1.15
    }))
    -1.14
    )}</
    -1.14
     EnglishChoose
    -1.12
     iſt
    -1.12
    POSITIVE LOGITS
     
    1.00
    {
    0.95
    (
    0.89
    “
    0.83
    "
    0.81
    $
    0.81
    <em>
    0.79
    <b>
    0.77
    <strong>
    0.75
    [
    0.72
    Act Density 0.054%

    No Known Activations