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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions involving variables and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.74
     الحره
    -0.65
    ſelf
    -0.64
    رشف
    -0.61
     ſtate
    -0.60
     Tinh
    -0.60
    DMETHOD
    -0.59
    ſelves
    -0.59
    ulaski
    -0.57
    endpush
    -0.56
    POSITIVE LOGITS
     Y
    3.35
     y
    3.22
    Y
    2.76
    y
    2.06
    getY
    1.91
     getY
    1.84
    Ｙ
    1.72
    setY
    1.68
     YC
    1.43
    YC
    1.43
    Act Density 0.714%

    No Known Activations