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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that express a sense of inquiry about reasons or explanations

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

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rollup
    -0.49
    CBM
    -0.48
    esu
    -0.47
     GSC
    -0.47
    UCC
    -0.47
    CMC
    -0.47
    IMC
    -0.45
     DRS
    -0.45
    ennan
    -0.45
     GCM
    -0.44
    POSITIVE LOGITS
     why
    1.85
    why
    1.70
     Why
    1.61
    Why
    1.60
     WHY
    1.53
    WHY
    1.47
     pourquoi
    1.38
     waarom
    1.27
     Warum
    1.27
    Pourquoi
    1.27
    Act Density 0.013%

    No Known Activations