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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of "at" followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "at" occurring in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lens
    -0.77
    FTWARE
    -0.71
    birds
    -0.69
    Pac
    -0.67
    fill
    -0.66
    Russ
    -0.66
    PLA
    -0.62
    vous
    -0.62
    film
    -0.61
    BOX
    -0.60
    POSITIVE LOGITS
     least
    1.23
    abase
    1.22
    onement
    1.04
    rial
    1.00
    rium
    0.91
     dusk
    0.84
    roph
    0.83
     intervals
    0.82
    oned
    0.82
    hens
    0.80
    Act Density 0.176%

    No Known Activations