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

    Neuronpedia

    INDEX
    Explanations

    round objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "round"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uras
    -0.69
    yer
    -0.69
    acca
    -0.67
    alez
    -0.67
    enez
    -0.67
     mathemat
    -0.66
    "},"
    -0.66
    ORY
    -0.64
    ionage
    -0.62
    rogens
    -0.61
    POSITIVE LOGITS
    abouts
    0.91
     round
    0.89
    about
    0.86
    trip
    0.85
    table
    0.84
     Round
    0.83
    dule
    0.81
    Round
    0.79
    worms
    0.75
    robe
    0.75
    Act Density 0.013%

    No Known Activations