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

    Neuronpedia

    INDEX
    Explanations

    the word "when" in various forms and contexts

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

    when, quand, quando

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.55
    nemia
    -0.37
     famí
    -0.36
     getLayout
    -0.35
    coroutines
    -0.34
     ytterligare
    -0.34
     taro
    -0.34
     fubject
    -0.34
    kof
    -0.34
     contribu
    -0.33
    POSITIVE LOGITS
     when
    1.70
    when
    1.67
     WHEN
    1.52
     quando
    1.50
     When
    1.44
    When
    1.42
     cuando
    1.41
    quando
    1.41
    WHEN
    1.40
    cuando
    1.35
    Act Density 0.131%

    No Known Activations