INDEX
    Explanations

    inquiries that seek explanations or justifications

    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.93
     myſelf
    -0.81
     Monfieur
    -0.75
    ſelf
    -0.75
     Efq
    -0.74
    ädie
    -0.71
     himſelf
    -0.68
    IUrlHelper
    -0.67
     ſever
    -0.66
     ſte
    -0.65
    POSITIVE LOGITS
     why
    1.06
     weshalb
    0.86
    why
    0.78
     reason
    0.78
    AndEndTag
    0.75
     pourquoi
    0.75
     razón
    0.74
     reasons
    0.73
     razão
    0.73
     Daarom
    0.71
    Act Density 0.184%

    No Known Activations