INDEX
    Explanations

    This neuron activates on mentions of judges and judicial titles (e.g., “Circuit Judge,” “Senior Circuit Judge,” “District Judge,” and judge names).

    New Auto-Interp
    Negative Logits
    εύ
    -0.06
    ATIVE
    -0.06
    Ê
    -0.06
     patriotic
    -0.06
                                                             
    -0.06
     ME
    -0.06
    "]');↵
    -0.06
    .Collectors
    -0.06
    -0.06
     POR
    -0.06
    POSITIVE LOGITS
    关于
    0.07
     balances
    0.06
     Invitation
    0.06
    larda
    0.06
     interstate
    0.06
    0.06
    �다
    0.06
    0.06
    0.06
     skept
    0.06
    Act Density 0.006%

    No Known Activations