INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     edging
    -0.08
     ফর
    -0.08
    =[
    -0.07
     Etter
    -0.07
    CRI
    -0.07
     prie
    -0.07
     يعتبر
    -0.07
     PR
    -0.07
     مراق
    -0.07
    -0.07
    POSITIVE LOGITS
     ideas
    0.11
    观点
    0.10
     ideias
    0.10
    ideas
    0.09
     ideeën
    0.09
    /themes
    0.09
     bubbles
    0.09
    /theme
    0.09
     мысли
    0.09
     тез
    0.09
    Act Density 0.017%

    No Known Activations