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

    Neuronpedia

    INDEX
    Explanations

    references to structured information or organized content, such as flowcharts and examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γοÏį
    -0.14
     بÙĪدÙĩ
    -0.14
    porto
    -0.14
    _AUX
    -0.14
    ilot
    -0.14
     à¹Ģà¸ŀราะ
    -0.14
    ä¼¼
    -0.13
     taboo
    -0.13
    æ·»
    -0.13
    loy
    -0.13
    POSITIVE LOGITS
    :↵
    0.21
    :↵↵
    0.19
    :č↵
    0.19
    ):↵
    0.19
    ]:↵
    0.18
    :</
    0.18
    ":↵
    0.17
     :↵
    0.17
    ':↵
    0.17
    :↵↵↵
    0.17
    Act Density 0.104%

    No Known Activations