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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and concepts, particularly related to modular arithmetic

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Baron
    -0.07
     Target
    -0.07
     target
    -0.07
    à¸Ħล
    -0.06
    fty
    -0.06
    hol
    -0.06
     Team
    -0.06
    us
    -0.06
     linear
    -0.06
    imal
    -0.06
    POSITIVE LOGITS
    ucene
    0.09
    ген
    0.07
    leys
    0.07
    Compression
    0.07
    iglia
    0.07
    .unsplash
    0.07
    indexed
    0.07
    eyh
    0.06
    ãĥ¼ãĤ¹
    0.06
    iani
    0.06
    Act Density 0.380%

    No Known Activations