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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating quantity or degree, such as "just," "more," and "most."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maal
    -0.17
    ieee
    -0.16
    oran
    -0.15
    asley
    -0.14
    tail
    -0.14
    ilig
    -0.13
    rk
    -0.13
    ardash
    -0.13
     HIP
    -0.12
     tow
    -0.12
    POSITIVE LOGITS
    Ïħμ
    0.14
    ampoline
    0.14
    ATAR
    0.14
    alles
    0.14
    RESSED
    0.13
     Darling
    0.13
    ADI
    0.13
    ItemAt
    0.13
    ATUS
    0.13
    urve
    0.13
    Act Density 0.289%

    No Known Activations