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

    Neuronpedia

    INDEX
    Explanations

    references to memory addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.69
     betweenstory
    -0.67
    //};
    -0.61
     Wikispecies
    -0.61
    cjs
    -0.61
    AccessorTable
    -0.60
     Lumpur
    -0.58
    MLLoader
    -0.58
     vom
    -0.58
    ęcz
    -0.57
    POSITIVE LOGITS
    Address
    1.77
    address
    1.38
     Address
    1.24
    getAddress
    1.15
    addr
    1.13
    ADDRESS
    1.10
    ddress
    1.06
     地址
    0.94
     ADDRESS
    0.90
     addr
    0.88
    Act Density 0.150%

    No Known Activations