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

    Neuronpedia

    INDEX
    Explanations

    categories or classifications within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugin
    -0.17
    auge
    -0.15
     Ùħرات
    -0.15
    Disposition
    -0.14
    _lite
    -0.14
    ÏĦεÏħ
    -0.14
    幸
    -0.14
    osi
    -0.14
    oleon
    -0.14
    èĸ
    -0.14
    POSITIVE LOGITS
     Archives
    0.19
     archives
    0.17
    648
    0.17
    endid
    0.15
     theory
    0.15
    orsche
    0.15
     Wat
    0.15
    ewise
    0.14
    archives
    0.14
     winners
    0.14
    Act Density 0.006%

    No Known Activations