INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.73
    addContainerGap
    -0.67
     ارو
    -0.61
     tartalomajánló
    -0.58
    ">
    
    
    -0.58
     Wain
    -0.57
     Central
    -0.57
    Margot
    -0.57
     Margot
    -0.57
    Ārējās
    -0.56
    POSITIVE LOGITS
     mic
    2.29
     Mic
    2.12
    Mic
    2.01
     mics
    1.91
     microphone
    1.82
    mic
    1.79
     mike
    1.70
     microphones
    1.65
     Microphone
    1.64
     MIC
    1.55
    Act Density 0.073%

    No Known Activations