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

    Neuronpedia

    INDEX
    Explanations

    information related to storage and memory

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to data storage and retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sky
    -0.78
    xxx
    -0.76
    lia
    -0.74
    eds
    -0.74
    naire
    -0.71
    lez
    -0.69
    atown
    -0.68
    adder
    -0.68
    alities
    -0.68
    ĪĴ
    -0.68
    POSITIVE LOGITS
     storing
    0.98
     secrets
    0.85
     stored
    0.81
    keeping
    0.78
    UFF
    0.77
    IER
    0.77
     shelves
    0.74
    arded
    0.73
     storage
    0.73
    abytes
    0.71
    Act Density 0.052%

    No Known Activations