INDEX
    Explanations

    punctuation and formatting marks

    New Auto-Interp
    Negative Logits
     Cald
    -0.17
    ³
    -0.14
    theon
    -0.14
    èĮĥ
    -0.14
    lover
    -0.13
     Audit
    -0.13
    Clazz
    -0.13
    popular
    -0.13
    ÑĢол
    -0.13
     Screw
    -0.13
    POSITIVE LOGITS
    iran
    0.14
    lemetry
    0.14
    ILED
    0.14
    413
    0.13
    /entity
    0.13
    ساÙĨÛĮ
    0.13
    Delimiter
    0.13
    asto
    0.13
     Lager
    0.13
    许
    0.13
    Act Density 0.003%

    No Known Activations