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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings, indicating a focus on sentence structure and grammar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AllWindows
    -0.19
    avras
    -0.17
    ObjectContext
    -0.16
    æĹıèĩªæ²»
    -0.15
    å¯Ł
    -0.15
    ãĥ¼ãĥ«
    -0.14
    NullOrEmpty
    -0.14
    erable
    -0.14
    akat
    -0.14
    æ·
    -0.14
    POSITIVE LOGITS
    ãģįãģª
    0.15
    725
    0.14
    ãģį
    0.14
    achinery
    0.14
    625
    0.13
    μι
    0.13
    938
    0.13
    ìĽIJìĿĺ
    0.13
    709
    0.13
    zero
    0.13
    Act Density 0.081%

    No Known Activations