INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     berühm
    0.72
     σειρά
    0.69
     äußerst
    0.68
     wundersch
    0.67
     kitap
    0.66
    Daten
    0.66
    Shapes
    0.66
    <unused1158>
    0.65
     пане
    0.64
     વિવિધ
    0.64
    POSITIVE LOGITS
     situation
    0.75
     transgression
    0.70
     ailment
    0.69
     damage
    0.67
     aggression
    0.65
     injury
    0.63
     disturbance
    0.63
     matter
    0.63
     affected
    0.63
     inflicted
    0.62
    Act Density 0.000%

    No Known Activations