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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "what."

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

    asking what or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.57
    __',
    -0.45
    ousand
    -0.43
    Vidite
    -0.43
    intios
    -0.42
    InstrumentedTest
    -0.42
    thâu
    -0.41
    eddah
    -0.41
     incarcerated
    -0.40
    UnusedPrivate
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.50
     What
    0.44
     TextAppearance
    0.44
    What
    0.44
    SuppressMessage
    0.43
    ínű
    0.42
    出版年
    0.42
     Wikiseite
    0.41
     doPost
    0.41
    Cuál
    0.40
    Act Density 0.004%

    No Known Activations