INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Restoration
    -0.08
     Retrieves
    -0.07
     Burton
    -0.07
    45
    -0.07
     dose
    -0.07
     restored
    -0.07
     bursting
    -0.07
     selectable
    -0.07
     baker
    -0.07
     astr
    -0.07
    POSITIVE LOGITS
     farewell
    0.13
     goodbye
    0.11
    0.10
    Bye
    0.10
     bye
    0.10
     afscheid
    0.09
     Bye
    0.09
     thro
    0.09
    няя
    0.09
     desped
    0.08
    Act Density 0.009%

    No Known Activations