INDEX
    Explanations

    concepts related to goals and outcomes

    New Auto-Interp
    Negative Logits
    kia
    0.53
    zäh
    0.52
    ine
    0.52
    0.50
    ко
    0.48
    ერთი
    0.48
    и
    0.47
    ordnet
    0.47
     చి
    0.47
    къ
    0.47
    POSITIVE LOGITS
     revolutionary
    0.51
     hatred
    0.49
    _{
    0.49
    Designed
    0.47
     vengeance
    0.43
     passe
    0.43
     venge
    0.42
     mystical
    0.42
     rivalry
    0.41
     Spartans
    0.40
    Act Density 0.000%

    No Known Activations