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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated contexts in dialogue

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

    dialogue opening quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.64
    Panamoan
    -0.64
     snippetHide
    -0.64
     esternos
    -0.61
     Normdatei
    -0.60
    TypedDataSet
    -0.60
     estekak
    -0.58
    rungsseite
    -0.57
    skrift
    -0.57
    hoeddwyd
    -0.56
    POSITIVE LOGITS
     "
    0.35
    「
    0.34
    ét
    0.33
    リヤ
    0.33
    äß
    0.33
     even
    0.32
    testens
    0.32
     „
    0.32
    }{*}{
    0.31
     mesmo
    0.31
    Act Density 0.005%

    No Known Activations