INDEX
    Explanations

    negative sentiment indicators

    New Auto-Interp
    Negative Logits
     автоном
    0.79
     antigüedad
    0.79
    0.71
    figur
    0.71
     করিতেছিল
    0.68
    anj
    0.67
     وتح
    0.67
    0.67
    ัป
    0.67
     แรก
    0.66
    POSITIVE LOGITS
     cough
    0.77
     reproach
    0.77
     bandages
    0.74
     stupid
    0.71
     glue
    0.70
     foolish
    0.69
     scare
    0.69
     greedy
    0.68
     scares
    0.67
    стить
    0.67
    Act Density 0.000%

    No Known Activations