INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    InputBorder
    -1.03
    PhysRev
    -0.91
    PhysRevLett
    -0.85
     useAppContext
    -0.84
    RectangleBorder
    -0.84
    abestanden
    -0.83
     ―――――
    -0.83
     photolibrary
    -0.82
     سكانية
    -0.82
    )‏
    -0.79
    POSITIVE LOGITS
    0.73
     you
    0.71
    ↵↵
    0.69
    0.60
      
    0.60
     I
    0.59
    Marshaller
    0.54
    <eos>
    0.54
     New
    0.53
     .
    0.52
    Act Density 0.090%

    No Known Activations