INDEX
    Explanations

    phrases related to discounts and promotions

    New Auto-Interp
    Negative Logits
    ally
    -0.16
    deb
    -0.15
    illery
    -0.15
    alian
    -0.15
    orrent
    -0.15
     kro
    -0.15
     altogether
    -0.14
    ibal
    -0.14
    itÃł
    -0.14
    isco
    -0.14
    POSITIVE LOGITS
     whenever
    0.17
    OLS
    0.17
    inois
    0.16
    gebra
    0.15
    615
    0.15
    cky
    0.14
    _CHUNK
    0.14
    OLF
    0.14
    909
    0.14
    backup
    0.14
    Act Density 0.118%

    No Known Activations