INDEX
    Explanations

    references to specific organizations, geographic locations, and community activities

    New Auto-Interp
    Negative Logits
    izr
    -0.16
    (u
    -0.15
    erland
    -0.15
    687
    -0.15
    679
    -0.14
     Dip
    -0.14
    ñana
    -0.14
    .clip
    -0.14
     wer
    -0.14
     Simone
    -0.14
    POSITIVE LOGITS
    PFN
    0.16
    ashi
    0.16
    ẹn
    0.15
    rays
    0.15
    ÙĦاÙĦ
    0.15
    jal
    0.14
    enin
    0.14
     milan
    0.14
    ammen
    0.14
    мелÑĮ
    0.14
    Act Density 0.076%

    No Known Activations