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

    Neuronpedia

    INDEX
    Explanations

    quantities of memory specified in gigabytes

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and storage capacities in devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icians
    -0.74
    unct
    -0.68
     precedence
    -0.64
    neum
    -0.62
    akespe
    -0.61
     resemb
    -0.60
    ople
    -0.60
     Dru
    -0.60
     Akin
    -0.59
     pronounce
    -0.59
    POSITIVE LOGITS
     GDDR
    1.04
    GB
    0.91
    abytes
    0.90
    ASE
    0.87
    UGE
    0.87
    bps
    0.85
    Ms
    0.83
     SSD
    0.83
    ottest
    0.80
     RAM
    0.80
    Act Density 0.013%

    No Known Activations