INDEX
    Explanations

    mathematical and statistical notation related to equations and functions

    Mathematical or code-related punctuation

    punctuation and symbols

    New Auto-Interp
    Negative Logits
    ":
    
    -1.05
    )");
    
    -1.04
    "):
    
    -0.96
    "];
    
    -0.94
    ':
    
    -0.92
    '));
    
    -0.86
    "));
    
    -0.85
    .");
    
    -0.84
    '];
    
    -0.83
    ")));
    
    -0.83
    POSITIVE LOGITS
      
    1.00
     ProtoMessage
    0.90
       
    0.84
    ScopeManager
    0.84
    
    0.82
    ,\
    0.80
     {\
    0.78
    0.78
    WireFormatLite
    0.77
    ~\
    0.77
    Act Density 3.475%

    No Known Activations