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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and their placements in sentences

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

    whose, which, who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.62
     ModelExpression
    -0.58
    NameInMap
    -0.57
    كويكب
    -0.55
    лтемелер
    -0.55
    WindowConstants
    -0.52
    XmlAccessType
    -0.51
     Emphasis
    -0.48
     Stretching
    -0.48
     Pasture
    -0.48
    POSITIVE LOGITS
     which
    0.65
     whose
    0.57
    whose
    0.51
     who
    0.46
    ซึ่ง
    0.44
     cuyos
    0.44
     الذي
    0.43
    ผู้
    0.42
    which
    0.42
     cuyo
    0.42
    Act Density 0.112%

    No Known Activations