INDEX
    Explanations

    font-related attributes in code

    New Auto-Interp
    Negative Logits
    SEQ
    -0.16
    craft
    -0.16
    igung
    -0.16
    лоп
    -0.15
     OP
    -0.15
    ediÄŁi
    -0.15
    ÏĦÏģι
    -0.15
    752
    -0.14
    Ñĥди
    -0.14
    ì±Ħ
    -0.14
    POSITIVE LOGITS
    enco
    0.17
    ÅĤad
    0.17
     provinc
    0.15
    kc
    0.15
    olib
    0.14
    ville
    0.14
    kol
    0.14
    èī¯
    0.14
     ÙĪÙĦ
    0.13
    Revision
    0.13
    Act Density 0.006%

    No Known Activations