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

    Neuronpedia

    INDEX
    Explanations

    inquiries about the reasons or causes behind various situations or phenomena

    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
     snippetHide
    -0.51
     NSCoder
    -0.50
    UnitTesting
    -0.49
    HasAnnotation
    -0.48
    ViewImports
    -0.47
    AutoScaleMode
    -0.47
    Portale
    -0.47
    izr
    -0.47
    DockStyle
    -0.47
     MotionEvent
    -0.47
    POSITIVE LOGITS
     why
    1.16
    why
    1.04
     waarom
    1.02
    Why
    1.02
     warum
    0.99
     dlaczego
    0.99
     hvorfor
    0.96
     Why
    0.95
     pourquoi
    0.94
     Warum
    0.94
    Act Density 0.016%

    No Known Activations