INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     invertir
    -0.08
     beats
    -0.08
    .spotify
    -0.07
    /operators
    -0.07
     calibration
    -0.07
     vente
    -0.07
     investing
    -0.07
    БУ
    -0.07
     engraving
    -0.07
    POSITIVE LOGITS
     refugee
    0.19
     refugees
    0.17
     refugi
    0.14
     humanitarian
    0.13
     Refuge
    0.13
     Flücht
    0.13
     asylum
    0.10
     opvang
    0.10
     homeless
    0.10
     refuge
    0.10
    Act Density 0.024%

    No Known Activations