INDEX
    Explanations

    attends to the marked tokens from the first token in the sequence to arbitrary following tokens

    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.13
    2:0.40
    3:0.04
    4:0.06
    5:0.08
    6:0.03
    7:0.11
    Negative Logits
    Kariera
    -0.38
     chromos
    -0.38
    VIAF
    -0.37
    astify
    -0.36
     estekak
    -0.36
    __':
    
    -0.34
     denture
    -0.34
     ingrat
    -0.34
    GOTREF
    -0.33
    Pautan
    -0.33
    POSITIVE LOGITS
    tahui
    0.35
    0.33
     '..
    0.32
    ]].
    0.30
    .\\
    0.29
    .]
    0.29
    alised
    0.28
    aimana
    0.28
    '));
    0.27
    .');
    0.27
    Act Density 0.991%

    No Known Activations