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

    Neuronpedia

    INDEX
    Explanations

    punctuation and grammar discussions

    np_max-act · gemini-2.0-flash

    sentences that include contextual usage of punctuation marks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     construed
    -0.06
     Components
    -0.06
     από
    -0.06
    ^^^^
    -0.06
     Polar
    -0.06
     much
    -0.06
     назна
    -0.06
     pagan
    -0.06
     cate
    -0.06
     Đề
    -0.05
    POSITIVE LOGITS
     cré
    0.07
    ][
    0.07
    untas
    0.06
    /*
↵
    0.06
     لل
    0.06
    avax
    0.06
     عملیات
    0.06
    �
    0.06
    \Application
    0.06
    "=>"
    0.06
    Act Density 0.016%

    No Known Activations