INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.62
     honour
    -0.50
     honourable
    -0.50
     Honour
    -0.49
    UserScript
    -0.49
    Diweddarwch
    -0.49
    Notae
    -0.48
     favourable
    -0.48
     centred
    -0.48
     doublet
    -0.48
    POSITIVE LOGITS
     iprot
    0.69
     للمعارف
    0.61
     Normdatei
    0.58
    MessageTagHelper
    0.55
    Demikian
    0.54
     Rule
    0.54
    writeFieldEnd
    0.53
    citep
    0.53
    eriks
    0.52
    ValueStyle
    0.52
    Act Density 0.012%

    No Known Activations