INDEX
    Explanations

    names of prominent political figures

    New Auto-Interp
    Negative Logits
    kö
    -0.15
    ê°ij
    -0.15
    MBER
    -0.15
    _INCREMENT
    -0.14
    andy
    -0.14
    .FileSystem
    -0.14
    @nate
    -0.14
    è¾ħ
    -0.14
    æĮ¯ãĤĬ
    -0.14
    евид
    -0.14
    POSITIVE LOGITS
    phin
    0.17
     Lav
    0.17
    enheim
    0.16
    ehr
    0.15
    107
    0.15
    kes
    0.15
    variants
    0.14
    eds
    0.14
    Liked
    0.14
    ĥ
    0.14
    Act Density 0.008%

    No Known Activations