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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     troubled
    1.66
     TIL
    1.48
     heavyweight
    1.40
     troubling
    1.29
     legible
    1.28
     numerator
    1.28
     assurance
    1.28
     systemic
    1.27
     Nietzsche
    1.27
     asylum
    1.27
    POSITIVE LOGITS
     g
    1.01
    cursors
    0.94
    C
    0.89
    Id
    0.88
     तिथ
    0.84
    T
    0.81
    من
    0.81
    cwd
    0.81
    éra
    0.80
    స్
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.