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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Begins with "A:" (likely an answer)

    np_acts-logits-general · gemini-2.0-flash

    answers to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.66
     príncipe
    -0.62
     للاسماء
    -0.57
    thâu
    -0.57
    Rüyada
    -0.56
    RenderAtEndOf
    -0.55
     صوتيه
    -0.54
     يتيمه
    -0.54
    يكب
    -0.53
     bezpiecze
    -0.53
    POSITIVE LOGITS
     I
    0.60
     yeah
    0.60
    Yeah
    0.59
    Anyway
    0.59
    Thanks
    0.58
     Anyway
    0.58
    Reply
    0.58
    Dear
    0.57
     Reply
    0.57
     Seems
    0.56
    Act Density 1.146%

    No Known Activations