INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     groupBox
    0.52
     நூற்ற
    0.51
    ypen
    0.49
    ಕ್ಕಾಗಿ
    0.48
    0.48
    aparikkh
    0.46
    गिन
    0.46
    0.45
    ısını
    0.45
    ঙ্খ
    0.45
    POSITIVE LOGITS
    Birds
    0.56
     Birds
    0.55
    Unique
    0.55
    a
    0.53
     Proper
    0.51
     
    0.50
    Journal
    0.48
     Novel
    0.48
    Proper
    0.47
    =
    0.47
    Act Density 0.003%

    No Known Activations