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

    Neuronpedia

    INDEX
    Explanations

    amounts of computer memory storage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of RAM capacities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unct
    -0.79
     abdom
    -0.65
     precedence
    -0.65
    inen
    -0.64
     licens
    -0.61
    ople
    -0.60
     Dean
    -0.60
     discipl
    -0.60
     showc
    -0.59
    zai
    -0.58
    POSITIVE LOGITS
    GB
    1.03
    UGE
    0.97
     GDDR
    0.93
    abytes
    0.84
     SSD
    0.81
    FFER
    0.77
    asper
    0.76
    Berry
    0.75
    oard
    0.75
    Ms
    0.74
    Act Density 0.011%

    No Known Activations