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

    Neuronpedia

    INDEX
    Explanations

    punctuations and conjunctions that indicate pauses or transitions in thought

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

    Punctuation followed by a discourse marker

    np_acts-logits-general · gemini-2.0-flash

    commas and semicolons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.48
    RTSN
    -0.47
     Medidas
    -0.46
    úsqueda
    -0.43
    babkan
    -0.42
     TAMBÉM
    -0.42
    titleMargin
    -0.41
     Herramientas
    -0.40
     Veuillez
    -0.40
    ₂+
    -0.40
    POSITIVE LOGITS
    TypedDataSet
    0.49
    出版年
    0.42
     abide
    0.41
     engraçadas
    0.41
     interact
    0.41
    llong
    0.39
     socialize
    0.39
     obey
    0.39
    참고
    0.39
     PV
    0.38
    Act Density 0.831%

    No Known Activations