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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of saving or preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sz
    -0.15
    usters
    -0.14
    /Foundation
    -0.14
    RAR
    -0.14
    .libs
    -0.14
    xico
    -0.14
    elerik
    -0.14
    ATEGORIES
    -0.14
    uese
    -0.13
    iphy
    -0.13
    POSITIVE LOGITS
    ÑĢовиÑĩ
    0.17
    enne
    0.16
    pz
    0.16
    dac
    0.15
    elta
    0.15
     Pell
    0.15
    leine
    0.14
    ierge
    0.14
    ataka
    0.14
    ille
    0.14
    Act Density 0.012%

    No Known Activations