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

    Neuronpedia

    INDEX
    Explanations

    time intervals indicated by numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time intervals or frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artisan
    -0.82
    usky
    -0.68
    ategy
    -0.68
    isky
    -0.67
    trak
    -0.66
     Flavoring
    -0.65
    itech
    -0.64
    agall
    -0.63
    archment
    -0.63
    quished
    -0.62
    POSITIVE LOGITS
     seconds
    1.07
     minutes
    1.06
     centimeters
    0.95
     clicks
    0.92
     mins
    0.91
     milliseconds
    0.91
     kilometres
    0.88
     cents
    0.85
    ths
    0.85
     kilometers
    0.85
    Act Density 0.034%

    No Known Activations