INDEX
    Explanations

    numerical values or codes in the text

    New Auto-Interp
    Negative Logits
    })),
    -0.78
    }}},
    -0.74
    ]]
    
    -0.73
    ']],
    -0.73
    czaj
    -0.73
    iedler
    -0.73
    													
    -0.72
    ANGEL
    -0.69
    Становништво
    -0.66
    ']))
    
    -0.64
    POSITIVE LOGITS
    0
    1.77
    0.99
    AndEndTag
    0.81
    awtextra
    0.79
    ۰
    0.79
    0.77
    𝟎
    0.74
    0.73
     Tencent
    0.72
     Scip
    0.70
    Act Density 2.412%

    No Known Activations