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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    agate
    -0.75
    ÃŁ
    -0.73
    pload
    -0.72
    vernment
    -0.68
     Consent
    -0.68
    */(
    -0.68
    audi
    -0.67
     Hear
    -0.67
    brance
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    POSITIVE LOGITS
     extremes
    0.72
     equ
    0.67
    age
    0.62
     boils
    0.62
     eq
    0.60
    ages
    0.60
    itarian
    0.60
     engagements
    0.59
     depending
    0.59
    tu
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.