INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     unnecessarily
    1.03
     संवै
    0.89
     needlessly
    0.88
    فا
    0.81
    अनु
    0.80
     contradicted
    0.79
    0.77
     negative
    0.76
     uncomfortable
    0.75
    ിക്കേണ്ട
    0.74
    POSITIVE LOGITS
     attacker
    1.39
     attackers
    1.39
     mastermind
    1.37
     perpetrator
    1.32
     motive
    1.31
     attacks
    1.28
     accomplice
    1.28
     getaway
    1.26
     perpetrators
    1.26
     attack
    1.23
    Act Density 0.311%

    No Known Activations