INDEX
    Explanations

    curly braces and formatting commands typical in LaTeX documents

    New Auto-Interp
    Negative Logits
    }^\
    -0.82
     Pelt
    -0.78
    ".$_
    -0.75
    ')")
    -0.72
    quiera
    -0.69
     =",
    -0.68
    '")
    -0.65
    /")
    -0.65
    ''')
    -0.64
    '])
    
    -0.64
    POSITIVE LOGITS
    {
    1.60
    {
    
    1.15
    {}{
    1.14
    ^{
    1.14
    []{
    1.11
    >{
    1.05
    _{
    1.04
    *{
    1.01
    }{
    1.01
    {(
    0.98
    Act Density 0.403%

    No Known Activations