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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     columnar
    0.80
     peruse
    0.76
     priced
    0.76
     suppose
    0.75
     paraphrase
    0.74
     assimilate
    0.73
     microbe
    0.71
     monologue
    0.71
    एड
    0.71
     cerebellar
    0.71
    POSITIVE LOGITS
    га
    0.87
     ê
    0.83
    Κ
    0.79
     С
    0.77
     К
    0.75
     случа
    0.75
     закры
    0.73
     не
    0.73
     значения
    0.73
     Г
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.