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

    Neuronpedia

    INDEX
    Explanations

    the presence of punctuation marks, specifically commas

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

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.64
     Normdatei
    -0.60
    InputBorder
    -0.59
    ulongan
    -0.58
    SharedCtor
    -0.58
     ब्रेकडाउन
    -0.58
     arşivlendi
    -0.55
    -0.54
    󰀄
    -0.54
    sizeCache
    -0.53
    POSITIVE LOGITS
    ↵↵
    0.47
    ↵
    0.42
    __()
    0.39
    “…”
    0.38
    ''',
    0.36
    これに
    0.35
    })),
    0.35
    ,",
    0.35
    会上
    0.34
      
    0.34
    Act Density 0.157%

    No Known Activations