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

    Neuronpedia

    INDEX
    Explanations

    specific commands related to scrolling through content

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of scrolling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤº
    -0.69
    stood
    -0.68
    OTA
    -0.66
    anol
    -0.64
    ften
    -0.63
    noxious
    -0.62
    ilities
    -0.60
     Fare
    -0.60
    jured
    -0.60
     Jed
    -0.59
    POSITIVE LOGITS
     Scroll
    0.94
    scroll
    0.91
     scroll
    0.87
     scrolling
    0.86
     scrolls
    0.86
    itzer
    0.84
    antry
    0.84
    ogue
    0.82
    chemy
    0.80
    bars
    0.79
    Act Density 0.020%

    No Known Activations