INDEX
    Explanations

    phrases that indicate financial transactions or agreements

    New Auto-Interp
    Negative Logits
    featureID
    -0.76
    Vidite
    -0.72
     AssemblyVersion
    -0.67
    UrlResolution
    -0.67
     Italijani
    -0.66
    AddTagHelper
    -0.65
    цезда
    -0.63
    antMatchers
    -0.63
     nakalista
    -0.62
    yarnpkg
    -0.60
    POSITIVE LOGITS
    
    0.56
     contemporain
    0.51
     Jurí
    0.50
     ornith
    0.49
     Espec
    0.47
    ↵↵↵↵↵
    0.47
     Económica
    0.47
    "]));
    0.47
     perist
    0.46
     pear
    0.46
    Act Density 0.767%

    No Known Activations