INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Referenties
    -0.53
     useParams
    -0.51
    voerd
    -0.51
     caneta
    -0.50
     Figuren
    -0.50
     Cullen
    -0.49
    attuale
    -0.48
    pasang
    -0.48
     fatores
    -0.48
     almofada
    -0.47
    POSITIVE LOGITS
     breakfast
    1.38
     Breakfast
    1.28
    Breakfast
    1.23
    breakfast
    1.20
     breakfasts
    1.18
     desayuno
    0.99
     desay
    0.88
     Frühstück
    0.79
     colazione
    0.76
    早餐
    0.73
    Act Density 0.002%

    No Known Activations