INDEX
    Explanations

    punctuation marks and symbols

    New Auto-Interp
    Negative Logits
    lio
    -0.16
    nel
    -0.15
    ain
    -0.14
     Cro
    -0.14
    rame
    -0.14
    el
    -0.14
    ello
    -0.14
    ìĸ´
    -0.14
    andal
    -0.14
    aped
    -0.13
    POSITIVE LOGITS
    wine
    0.17
    abus
    0.16
    webkit
    0.16
     ΣÏį
    0.14
    kos
    0.14
    CJK
    0.14
    osaur
    0.14
    æĺŃ
    0.13
    kem
    0.13
     rich
    0.13
    Act Density 0.038%

    No Known Activations