INDEX
    Explanations

    numerals and mathematical symbols

    New Auto-Interp
    Negative Logits
     {},
    
    -0.58
    "]));
    -0.57
    ")));
    
    -0.56
    .")]
    -0.55
     spécial
    -0.52
     '*')
    -0.52
    .}}
    -0.52
    Origem
    -0.50
    }\]
    -0.50
    icznych
    -0.50
    POSITIVE LOGITS
    TemporalType
    0.84
    qrstuvwxyz
    0.81
    +#+#
    0.76
    EDEFAULT
    0.73
    
    0.73
    complexContent
    0.69
    aarrggbb
    0.68
     surla
    0.66
    mtrl
    0.65
     OMITBAD
    0.65
    Act Density 0.001%

    No Known Activations