INDEX
    Explanations

    verbs indicating actions or changes

    New Auto-Interp
    Negative Logits
     Dane
    -0.15
    pron
    -0.15
    quette
    -0.15
    BJECT
    -0.15
     Neville
    -0.14
    cour
    -0.14
    /operators
    -0.14
    uddle
    -0.14
    ł
    -0.14
    avicon
    -0.14
    POSITIVE LOGITS
    eturn
    0.16
    ̣
    0.15
    εÏį
    0.15
    .googleapis
    0.14
    ander
    0.14
    íĮħ
    0.14
    lius
    0.14
    ItemClick
    0.14
    agen
    0.13
    ucks
    0.13
    Act Density 0.100%

    No Known Activations