INDEX
    Explanations

    introductory phrases and transitional phrases indicating the start of sentences or clauses

    New Auto-Interp
    Negative Logits
    etri
    -0.18
    rvé
    -0.16
     hoch
    -0.16
    fal
    -0.14
    iversal
    -0.14
    hq
    -0.14
     nearest
    -0.14
    ries
    -0.13
     Carn
    -0.13
    ahas
    -0.13
    POSITIVE LOGITS
    alue
    0.16
    tie
    0.16
    orough
    0.15
    Additionally
    0.15
     Additionally
    0.15
    ÑĤап
    0.15
     nữa
    0.14
    tabpanel
    0.14
    dÄĽ
    0.14
    å¼Ħ
    0.14
    Act Density 0.102%

    No Known Activations