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

    Neuronpedia

    INDEX
    Explanations

    terms related to computer processing power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processing capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.76
    olson
    -0.70
    ortium
    -0.68
    inav
    -0.66
    show
    -0.65
    gets
    -0.64
     railing
    -0.62
    verty
    -0.62
     oblig
    -0.62
    legged
    -0.61
    POSITIVE LOGITS
    ional
    0.89
     processing
    0.78
    ions
    0.73
     Processing
    0.72
     processors
    0.72
    Memory
    0.71
     horsepower
    0.69
     cores
    0.69
     throughput
    0.69
    itive
    0.68
    Act Density 0.054%

    No Known Activations