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

    Neuronpedia

    INDEX
    Explanations

    references to storage capacity in gigabytes

    oai_token-act-pair · gpt-3.5-turbo

    references to storage capacities and specifications of devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     licens
    -0.69
    igon
    -0.68
    deals
    -0.66
    zai
    -0.65
    inel
    -0.61
     plur
    -0.60
    ople
    -0.59
    struction
    -0.58
     guiActiveUn
    -0.58
    stal
    -0.58
    POSITIVE LOGITS
    GB
    1.16
    UGE
    0.96
     GB
    0.93
     GDDR
    0.86
    FFER
    0.85
    oard
    0.77
     SSD
    0.72
    abytes
    0.72
    ilit
    0.72
    ertodd
    0.72
    Act Density 0.006%

    No Known Activations