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

    Neuronpedia

    INDEX
    Explanations

    values of hardware components, such as graphics cards and CPUs

    oai_token-act-pair · gpt-3.5-turbo

    references to graphic cards and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.79
    senal
    -0.72
    querque
    -0.72
     tradem
    -0.72
    attled
    -0.69
    mble
    -0.69
    ourge
    -0.67
    achus
    -0.65
     peac
    -0.65
    ort
    -0.64
    POSITIVE LOGITS
     ILCS
    1.03
    50
    0.97
    wagen
    0.91
    MJ
    0.89
    ENCY
    0.86
    504
    0.82
    Apps
    0.82
     Shades
    0.80
    ishers
    0.79
    48
    0.78
    Act Density 0.039%

    No Known Activations