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

    Neuronpedia

    INDEX
    Explanations

    the word "pie" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to pie and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iveness
    -0.89
    ulk
    -0.76
    spring
    -0.73
    sers
    -0.72
     Examiner
    -0.71
    iqueness
    -0.69
    nen
    -0.64
    strong
    -0.64
    angers
    -0.63
     EDITION
    -0.63
    POSITIVE LOGITS
     pies
    1.05
    cing
    1.03
    ced
    1.03
     pie
    1.01
    pie
    0.97
     crust
    0.95
    Pie
    0.92
     Pie
    0.88
    cence
    0.84
    zo
    0.82
    Act Density 0.033%

    No Known Activations