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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     usual
    0.73
     sắp
    0.70
     stillness
    0.70
    逓
    0.70
     most
    0.68
     cé
    0.68
     marque
    0.68
     Practically
    0.66
     performer
    0.65
     ste
    0.64
    POSITIVE LOGITS
    abhut
    0.92
    ਰ
    0.89
    ний
    0.87
    ر
    0.87
    ী
    0.86
    nants
    0.79
    agiarism
    0.79
    iphat
    0.79
    رى
    0.77
    ਬਰ
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.