INDEX
    Explanations

    specific names and locations, particularly related to people and places

    New Auto-Interp
    Negative Logits
    ÑįÑĤомÑĥ
    -0.16
    neutral
    -0.16
    itmap
    -0.15
    iniz
    -0.14
    ForResult
    -0.14
    incess
    -0.14
    737
    -0.14
    åºŃ
    -0.13
    ADO
    -0.13
    norm
    -0.13
    POSITIVE LOGITS
    ules
    0.15
     tac
    0.14
    igers
    0.14
    AZY
    0.14
    kov
    0.14
    ULATE
    0.14
     Milan
    0.13
     seni
    0.13
    rowsable
    0.13
     Pul
    0.13
    Act Density 0.875%

    No Known Activations