INDEX
    Explanations

    attends to color values from associated numeric representations

    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.13
    2:0.08
    3:0.08
    4:0.11
    5:0.04
    6:0.08
    7:0.27
    Negative Logits
    はじめに
    -0.34
     مرئيه
    -0.32
    Tikang
    -0.31
    ]`
    -0.30
    ).__
    -0.28
     sukienka
    -0.28
    %"),
    -0.28
    %");
    -0.28
    nourriture
    -0.28
    )';
    -0.27
    POSITIVE LOGITS
     Burr
    0.39
    much
    0.33
    ///</
    0.32
     intptr
    0.29
    DebuggerNonUser
    0.29
     Much
    0.29
    Much
    0.29
    VersionUID
    0.29
    fram
    0.28
    GraphicsUnit
    0.28
    Act Density 0.025%

    No Known Activations