INDEX
    Explanations

    concepts related to political and social issues

    New Auto-Interp
    Negative Logits
    pNet
    -0.17
    REDENTIAL
    -0.16
    icker
    -0.16
    ortal
    -0.15
    座
    -0.15
    pdb
    -0.15
    elsey
    -0.15
    mdb
    -0.14
    pg
    -0.14
    }elseif
    -0.14
    POSITIVE LOGITS
     older
    0.21
     Older
    0.19
     oldest
    0.18
     ancient
    0.17
     familiar
    0.16
     old
    0.16
    èĥĮ
    0.16
    older
    0.15
     antiqu
    0.15
     backing
    0.15
    Act Density 0.001%

    No Known Activations