INDEX
    Explanations

    phrases related to personal feelings and relationships

    New Auto-Interp
    Negative Logits
    onom
    -0.18
     íķ´ëĭ¹
    -0.16
    uj
    -0.16
     تÙĦÙĥ
    -0.15
    outes
    -0.15
    ields
    -0.15
    those
    -0.15
    ache
    -0.15
    ahy
    -0.14
    çĴ
    -0.14
    POSITIVE LOGITS
     eso
    0.52
     isso
    0.46
     cela
    0.45
     ello
    0.38
     ذÙĦÙĥ
    0.38
     váºŃy
    0.35
     THAT
    0.35
     thats
    0.34
     esto
    0.34
     ìĿ´ëĬĶ
    0.33
    Act Density 0.477%

    No Known Activations