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

    Neuronpedia

    INDEX
    Explanations

    words related to Central Processing Units (CPUs)

    oai_token-act-pair · gpt-3.5-turbo

    references to CPU specifications and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reek
    -0.80
    lie
    -0.76
     Faust
    -0.72
    selves
    -0.72
    red
    -0.70
    zag
    -0.67
    ivalent
    -0.66
     Mayweather
    -0.66
    ership
    -0.66
     Horizons
    -0.65
    POSITIVE LOGITS
    PDATE
    1.26
     utilization
    0.90
     cores
    0.89
    Boss
    0.87
     accelerator
    0.80
     architectures
    0.79
    EED
    0.78
     sockets
    0.76
    intel
    0.76
     overcl
    0.74
    Act Density 0.017%

    No Known Activations