INDEX
    Explanations

    references to pets and animals

    New Auto-Interp
    Negative Logits
    orgh
    -0.18
    оÑĢод
    -0.16
    andon
    -0.15
    anh
    -0.15
    #ad
    -0.15
     Morav
    -0.15
    داÙĨ
    -0.14
     Natal
    -0.14
    iant
    -0.14
    groupBox
    -0.14
    POSITIVE LOGITS
     Spark
    0.19
     Spot
    0.19
     Shadow
    0.18
     Brut
    0.18
     Fritz
    0.17
     Spirit
    0.16
    Shadow
    0.16
    Spark
    0.16
     OT
    0.16
     Fl
    0.16
    Act Density 0.352%

    No Known Activations