INDEX
    Explanations

    names and details related to historical figures and events

    New Auto-Interp
    Negative Logits
     à¤¬à¤ľ
    -0.15
     Abr
    -0.14
    ottom
    -0.14
     FAQs
    -0.14
     Hag
    -0.13
    thro
    -0.13
    umo
    -0.13
     Bere
    -0.13
     incid
    -0.13
     Filter
    -0.13
    POSITIVE LOGITS
     kind
    0.27
     vä
    0.25
    kind
    0.25
    Kind
    0.24
     heir
    0.23
     KIND
    0.22
     Kind
    0.21
    _kind
    0.20
    .kind
    0.20
     adopt
    0.20
    Act Density 0.051%

    No Known Activations