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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or qualifications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oss
    -0.15
    pis
    -0.14
    938
    -0.14
    encil
    -0.14
     inconsistent
    -0.14
    idian
    -0.14
    ristol
    -0.13
     خط
    -0.13
    ız
    -0.13
     Buck
    -0.13
    POSITIVE LOGITS
    -lfs
    0.15
    ÑĨеÑģ
    0.15
    rette
    0.15
    ¹
    0.15
    ughs
    0.15
     {{--<
    0.15
    LOCKS
    0.14
    readcrumbs
    0.14
    arges
    0.14
    ickey
    0.14
    Act Density 0.008%

    No Known Activations