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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARROLL
    -0.68
     TextStyle
    -0.67
     MotionEvent
    -0.67
    mẫu
    -0.66
    HtmlAttribute
    -0.63
    oubted
    -0.62
    akterysty
    -0.62
    ">//
    -0.62
    __":
    -0.61
    inette
    -0.61
    POSITIVE LOGITS
    up
    4.15
    Up
    3.51
     Up
    3.25
    UP
    3.00
     up
    2.97
     UP
    2.61
    ups
    2.60
     ups
    1.93
    アップ
    1.92
    Ups
    1.88
    Act Density 0.126%

    No Known Activations