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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     know
    -0.87
     Know
    -0.80
     understood
    -0.79
     understand
    -0.75
    Know
    -0.75
    know
    -0.71
     known
    -0.71
     Known
    -0.70
     Understand
    -0.69
     recognized
    -0.68
    POSITIVE LOGITS
    WriteBarrier
    0.63
    PhysRev
    0.54
     well
    0.50
    {}/
    0.49
     CreateTagHelper
    0.49
    )"),
    0.47
    NamedQueries
    0.47
    randrange
    0.46
     att
    0.46
     kasarigan
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.