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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format (MM/DD/YYYY)

    oai_token-act-pair · gpt-3.5-turbo

    specific date formats and patterns related to timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.79
    ocene
    -0.78
    olson
    -0.72
     simultane
    -0.71
    everal
    -0.68
    cube
    -0.66
     exha
    -0.62
    ordan
    -0.62
    tones
    -0.61
     proport
    -0.61
    POSITIVE LOGITS
    00
    0.82
    iquette
    0.78
    raction
    0.76
    003
    0.71
    ŃĶ
    0.69
    01
    0.68
    inen
    0.67
     02
    0.67
    ress
    0.67
    (-
    0.67
    Act Density 0.019%

    No Known Activations