INDEX
    Explanations

    The neuron flags the appearance of the phrase “Published Opinion” in legal case citations.

    New Auto-Interp
    Negative Logits
    -0.07
     deposits
    -0.07
     ldap
    -0.06
     nie
    -0.06
     Pollution
    -0.06
     hairstyle
    -0.06
    -Sep
    -0.06
    loi
    -0.06
     Brew
    -0.06
     vým
    -0.06
    POSITIVE LOGITS
     newItem
    0.06
    )}"↵
    0.06
    >";
    ↵
    0.06
     familiarity
    0.06
     prior
    0.06
    ляли
    0.06
    	I
    0.05
     CLK
    0.05
    Tại
    0.05
    accuracy
    0.05
    Act Density 0.001%

    No Known Activations