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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references related to measurements or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ..↵↵↵↵
    -0.14
     ëĦ¤ìĿ´íĬ¸
    -0.14
     zev
    -0.14
     [-]:
    -0.14
    ÃĹ↵↵
    -0.14
     सप
    -0.14
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.13
     ìĥĪê¸Ģ
    -0.13
    (íģ¬ê¸°
    -0.13
    ỳ
    -0.13
    POSITIVE LOGITS
    0.59
    10
    0.21
    12
    0.21
    7
    0.20
    8
    0.20
    9
    0.20
    30
    0.20
    130
    0.20
    120
    0.19
    1
    0.19
    Act Density 2.489%

    No Known Activations