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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending structures in the text

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

    DONALD Trump Jr

    np_acts-logits-general · gemini-2.5-flash-lite

    the ends of sentences or discourse segments (sentence-final punctuation/turn boundaries).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     estekak
    -0.63
     iż
    -0.63
    SourceChecksum
    -0.60
    共に
    -0.60
    WebElementEntity
    -0.57
     אשר
    -0.55
     deemed
    -0.53
     kaarangay
    -0.52
    featureID
    -0.52
     столь
    -0.52
    POSITIVE LOGITS
     scary
    0.52
     Außerdem
    0.51
    Außerdem
    0.50
     Deshalb
    0.48
     democracia
    0.48
     malades
    0.47
     scared
    0.47
     stuff
    0.47
     malade
    0.47
     sauf
    0.46
    Act Density 0.266%

    No Known Activations