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

    Neuronpedia

    INDEX
    Explanations

    mentions and discussions of memory in a computer system context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of memory usage and related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qqa
    -0.80
     Riy
    -0.76
    jon
    -0.73
    glers
    -0.72
    bara
    -0.71
    zag
    -0.71
    Ĭ±
    -0.70
    keye
    -0.70
    nen
    -0.69
    ŃĶ
    -0.69
    POSITIVE LOGITS
     allocation
    1.01
     storage
    0.91
     consolidation
    0.89
     dumps
    0.89
     utilization
    0.89
     bandwidth
    0.88
     allocations
    0.87
     subsystem
    0.86
     fragmentation
    0.85
     allocated
    0.83
    Act Density 0.033%

    No Known Activations