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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas, indicating sentence boundaries or continuations

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

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enllaces
    -0.39
     Roskov
    -0.36
     kasarigan
    -0.36
    tehenden
    -0.35
    :✨
    -0.35
    ภู
    -0.34
    жника
    -0.34
     sidste
    -0.33
    Халык
    -0.31
     li
    -0.31
    POSITIVE LOGITS
     BoxDecoration
    0.60
    AndEndTag
    0.55
     Projektu
    0.54
    CloseOperation
    0.54
    XmlAccessorType
    0.52
    BufferException
    0.52
    Parcelize
    0.52
     ſind
    0.52
     EconPapers
    0.52
     ſta
    0.51
    Act Density 0.282%

    No Known Activations