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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     type
    0.58
     is
    0.55
    type
    0.54
     à
    0.50
     snippet
    0.49
     ASCII
    0.49
     satisfies
    0.46
     Exception
    0.46
     Types
    0.46
     Dirichlet
    0.46
    POSITIVE LOGITS
     own
    0.88
     eigenes
    0.67
     собстве
    0.67
     propia
    0.63
     eigener
    0.61
     eigenen
    0.59
     собствен
    0.59
    自身の
    0.59
     włas
    0.56
     propias
    0.54
    Act Density 0.474%

    No Known Activations