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

    Neuronpedia

    INDEX
    Explanations

    references to different hardware specifications, primarily focused on bits and storage capacities

    oai_token-act-pair · gpt-3.5-turbo

    references to computer architecture and specifications related to 64-bit systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andise
    -0.77
    ashtra
    -0.72
     Foley
    -0.68
    urus
    -0.67
    ichita
    -0.66
     Rasmussen
    -0.66
    icago
    -0.66
    ansen
    -0.66
    acus
    -0.66
    orical
    -0.63
    POSITIVE LOGITS
    bit
    1.09
    Bit
    0.97
    GB
    0.95
     bytes
    0.95
    kHz
    0.93
    384
    0.89
    kB
    0.88
    BIT
    0.85
     byte
    0.83
    Gb
    0.81
    Act Density 0.071%

    No Known Activations