INDEX
    Explanations

    This neuron detects the “ORDER AND JUDGMENT” heading (and similar judgment/order section titles) in appellate court documents.

    New Auto-Interp
    Negative Logits
     anything
    -0.08
     ausp
    -0.07
    offline
    -0.07
    _fatal
    -0.06
     انجام
    -0.06
    .Th
    -0.06
     demanded
    -0.06
    _path
    -0.06
     premium
    -0.06
     toys
    -0.06
    POSITIVE LOGITS
    :::::::::::::
    0.07
     мик
    0.06
    렸다
    0.06
     direkt
    0.06
    тивного
    0.06
    (Double
    0.06
     доз
    0.06
     subparagraph
    0.06
    jsc
    0.06
    元素
    0.06
    Act Density 0.001%

    No Known Activations