INDEX
    Explanations

    This neuron detects terminology around political fundraising and campaign contributions.

    words related to political contributions and campaign finance.

    New Auto-Interp
    Negative Logits
     Ελλην
    -0.06
     สำ
    -0.06
     zoals
    -0.06
     TestCase
    -0.06
    _gender
    -0.06
    러스
    -0.06
    icolon
    -0.06
    goods
    -0.06
    care
    -0.06
    sembly
    -0.06
    POSITIVE LOGITS
    	cmd
    0.07
    EF
    0.07
     centrif
    0.06
     meinen
    0.06
     polov
    0.06
     döneminde
    0.06
     QUI
    0.06
     Smooth
    0.06
     spec
    0.06
    ]"
    0.06
    Act Density 0.006%

    No Known Activations