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

    Neuronpedia

    INDEX
    Explanations

    dates represented in the format "MM/DD/YYYY"

    oai_token-act-pair · gpt-3.5-turbo

    patterns of asterisks and lines, possibly indicating sections or emphasis in text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.67
     clipping
    -0.65
    ollar
    -0.64
    ¿½
    -0.63
    arest
    -0.63
    aeper
    -0.62
     surfing
    -0.62
    gel
    -0.61
     hemor
    -0.61
    anan
    -0.60
    POSITIVE LOGITS
    */
    0.85
    =-=-
    0.80
     ¯
    0.74
    =-
    0.74
    ¯
    0.71
     =================================================================
    0.70
    ï¸
    0.69
    ===
    0.68
    export
    0.66
    *****
    0.65
    Act Density 0.072%

    No Known Activations