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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating sentence endings and questions

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

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $_(
    -0.65
     betweenstory
    -0.65
     doInBackground
    -0.63
    ロウィン
    -0.62
    <unused68>
    -0.61
    [@BOS@]
    -0.60
    <unused14>
    -0.60
    <unused23>
    -0.60
    <unused3>
    -0.60
    <unused28>
    -0.60
    POSITIVE LOGITS
    RenderAtEndOf
    0.42
     resourceCulture
    0.39
     Gerade
    0.36
    istung
    0.31
    qquad
    0.30
    article
    0.29
    AndEndTag
    0.29
     الض
    0.28
    ity
    0.28
    UTIVE
    0.28
    Act Density 0.022%

    No Known Activations