INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     gim
    -0.06
    _columns
    -0.06
    DOG
    -0.06
    -0.06
    idUser
    -0.06
    getTable
    -0.06
     BLE
    -0.06
    Lambda
    -0.06
     zg
    -0.06
    apos
    -0.06
    POSITIVE LOGITS
    @Inject
    0.06
    igrate
    0.06
     sexism
    0.06
    дяки
    0.06
    bla
    0.06
    _Al
    0.06
     partic
    0.06
    andise
    0.06
     addictive
    0.06
     жовт
    0.05
    Act Density 0.002%

    No Known Activations