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

    Neuronpedia

    INDEX
    Explanations

    mentions of the preposition "at" indicating specific locations or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Berry
    -0.73
    Fed
    -0.68
    FTWARE
    -0.68
    Pac
    -0.68
    advertising
    -0.67
    BOX
    -0.66
    Assistant
    -0.62
    MORE
    -0.62
    Shell
    -0.61
    bender
    -0.61
    POSITIVE LOGITS
     least
    1.27
    onement
    1.17
    rium
    1.03
    las
    1.01
    abase
    1.00
    rial
    0.98
     dusk
    0.92
    roph
    0.90
     intervals
    0.87
    oning
    0.87
    Act Density 0.158%

    No Known Activations