INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Figma
    0.47
     Гор
    0.44
     стре
    0.43
    checkmark
    0.43
    高雄
    0.43
     Ryzen
    0.42
    tmux
    0.41
    0.41
     Puppy
    0.40
    koi
    0.40
    POSITIVE LOGITS
     SOAP
    1.77
     soap
    1.73
     Soap
    1.57
    Soap
    1.57
    soap
    1.51
    wsdl
    1.45
     soaps
    1.45
     XML
    1.33
     xml
    1.23
    XML
    1.16
    Act Density 0.011%

    No Known Activations