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

    Neuronpedia

    INDEX
    Explanations

    various types of punctuation and formatting in text

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

    Comes before brackets or colons

    np_acts-logits-general · gemini-2.0-flash

    section\[letter]:[identifier]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      (
    -0.74
    帖最后由
    -0.70
    NSYLVANIA
    -0.69
    씩
    -0.67
    xffffffff
    -0.64
     للمعارف
    -0.62
    Външни
    -0.59
    Weiterlesen
    -0.59
    ].[
    -0.59
     hasard
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.72
     NSCoder
    0.52
    HomeAsUpEnabled
    0.51
     Exactos
    0.50
     épaules
    0.49
     insom
    0.48
     [:
    0.47
     stället
    0.45
     shea
    0.45
     joaat
    0.44
    Act Density 0.380%

    No Known Activations