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

    Neuronpedia

    INDEX
    Explanations

    mentions of storage capacities in electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to storage capacities and memory specifications of devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akespe
    -0.68
     precedence
    -0.66
     abdom
    -0.65
     Osw
    -0.63
    icians
    -0.63
     dispatcher
    -0.62
    ople
    -0.61
     nomine
    -0.61
     performed
    -0.59
    breeding
    -0.58
    POSITIVE LOGITS
     GDDR
    1.02
    +.
    0.95
    bps
    0.95
    abytes
    0.91
    +)
    0.90
    +,
    0.88
     SSD
    0.82
    +
    0.81
    GB
    0.81
    Percent
    0.79
    Act Density 0.015%

    No Known Activations