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

    Neuronpedia

    INDEX
    Explanations

    cookie-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cookies, particularly in various contexts and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SI
    -0.74
    WAYS
    -0.73
    ashtra
    -0.72
    abouts
    -0.69
    rior
    -0.66
    ional
    -0.65
    involved
    -0.64
    WARD
    -0.63
     Tsarnaev
    -0.63
    ities
    -0.62
    POSITIVE LOGITS
     cookies
    1.27
     dough
    1.17
     cookie
    1.07
     jar
    1.06
     Cookies
    0.98
     jars
    0.98
     Clicker
    0.98
     Cookie
    0.95
     cutter
    0.94
    cookie
    0.90
    Act Density 0.018%

    No Known Activations