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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols, particularly commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endor
    -0.15
    æµ´
    -0.15
    iese
    -0.15
    ken
    -0.15
    CUS
    -0.14
     दर
    -0.14
    stras
    -0.14
    -Clause
    -0.14
    cus
    -0.13
     underlying
    -0.13
    POSITIVE LOGITS
    chner
    0.17
    ãĤ´ãĥª
    0.15
    .qml
    0.15
    ãĥ³ãĥĩ
    0.15
    ucene
    0.14
    isci
    0.14
     Lage
    0.14
    ucer
    0.14
     Hod
    0.14
    ган
    0.13
    Act Density 0.011%

    No Known Activations