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

    Neuronpedia

    INDEX
    Explanations

    numerical values and classifications related to standards, regulations, and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plex
    -0.15
    castle
    -0.15
    erli
    -0.14
    unt
    -0.14
    anko
    -0.14
    mî
    -0.13
    essel
    -0.13
    168
    -0.13
    tery
    -0.13
    ongyang
    -0.13
    POSITIVE LOGITS
    /type
    0.23
    ì§ľ
    0.16
    ï¸ı
    0.15
    bis
    0.15
    âĢ³
    0.15
    /Form
    0.15
     æ¹
    0.14
    ê°ľë¥¼
    0.14
    .tm
    0.14
     Mun
    0.14
    Act Density 0.058%

    No Known Activations