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

    Neuronpedia

    INDEX
    Explanations

    phrases related to combinatorial choices and probabilities in hypothetical scenarios

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

    probability of picking items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.56
     dAtA
    -0.48
    proposed
    -0.44
    cuadro
    -0.42
     TRUCK
    -0.42
    amet
    -0.41
    induction
    -0.40
    SharedDtor
    -0.40
    veget
    -0.40
    quiet
    -0.40
    POSITIVE LOGITS
    NOPQRST
    0.54
    WebServlet
    0.49
     JpaRepository
    0.45
     surla
    0.44
    TagMode
    0.42
    Hentet
    0.40
     PopupWindow
    0.40
     bureaus
    0.37
    geslacht
    0.37
    yntaxException
    0.36
    Act Density 0.836%

    No Known Activations