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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their roles or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MT
    -0.16
    AttributeName
    -0.15
    anela
    -0.15
    901
    -0.14
    _HOT
    -0.14
    zens
    -0.14
    onen
    -0.14
    áš
    -0.14
    eger
    -0.14
     nid
    -0.14
    POSITIVE LOGITS
    igli
    0.18
     belong
    0.17
    æĿ¥èĩª
    0.17
     thuá»Ļc
    0.16
    æĺ¯ä¸ª
    0.15
     belonged
    0.15
    éļ
    0.15
    ê°IJ
    0.15
     ÙĪÙĩÙĪ
    0.15
    æĺ¯ä¸Ģ个
    0.15
    Act Density 0.207%

    No Known Activations