INDEX
    Explanations

    emotions and sentiments related to loss and tragedy

    New Auto-Interp
    Negative Logits
     hilar
    -0.15
    izin
    -0.14
    umo
    -0.14
    uria
    -0.14
    ihar
    -0.14
    778
    -0.14
    kü
    -0.14
    اء
    -0.14
    055
    -0.13
    rax
    -0.13
    POSITIVE LOGITS
     families
    0.20
     innocent
    0.17
     innoc
    0.16
    amilies
    0.16
     Families
    0.16
     lives
    0.16
     :(
    0.15
    æ°¸ä¹ħ
    0.15
     Innoc
    0.15
     forever
    0.15
    Act Density 0.184%

    No Known Activations