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

    Neuronpedia

    INDEX
    Explanations

    editor's notes and updates in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Editor's note" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.76
    ĪĴ
    -0.71
    abouts
    -0.65
    Downloadha
    -0.62
     woodland
    -0.60
    illy
    -0.60
    stones
    -0.60
    plings
    -0.59
    ught
    -0.58
    growing
    -0.58
    POSITIVE LOGITS
     Picks
    0.99
    Publisher
    0.86
     pse
    0.76
    Edge
    0.76
    iences
    0.74
     Reviews
    0.73
    lish
    0.69
    ש
    0.69
    lisher
    0.69
    Journal
    0.68
    Act Density 0.077%

    No Known Activations