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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (pDX
    -0.07
     ني
    -0.07
     looks
    -0.07
    舐
    -0.07
    Entr
    -0.07
    戰
    -0.07
     describes
    -0.07
    mé
    -0.06
    跟随
    -0.06
    还是会
    -0.06
    POSITIVE LOGITS
     RUNNING
    0.07
     Oakland
    0.07
    /unit
    0.07
     SolidColorBrush
    0.07
     Revised
    0.06
    _Select
    0.06
     BLUE
    0.06
    white
    0.06
    :before
    0.06
     Observation
    0.06
    Act Density 0.017%

    No Known Activations