INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    щем
    0.47
     perhaps
    0.45
     characterised
    0.43
     đó
    0.41
    0.41
     herring
    0.40
    žio
    0.40
     surfboard
    0.40
     general
    0.39
    çon
    0.39
    POSITIVE LOGITS
    <unused278>
    0.47
     அடிப்பட
    0.44
    <unused2016>
    0.43
    咳嗽
    0.43
    <unused1828>
    0.43
     সবকিছু
    0.41
     ampla
    0.41
     außergewöhn
    0.41
     леген
    0.40
    បន្ថ
    0.40
    Act Density 0.003%

    No Known Activations