INDEX
    Explanations

    references to news outlets and publications

    Publications like "Times", "Wired", "Forbes"

    New Auto-Interp
    Negative Logits
    fromnode
    -0.75
    Tikang
    -0.61
    -0.59
    LookAnd
    -0.56
    RTDA
    -0.55
    RTLR
    -0.54
     transfieras
    -0.52
    󠁴
    -0.51
     MainAxisSize
    -0.51
    OGND
    -0.50
    POSITIVE LOGITS
    washingtonpost
    0.41
     Newsweek
    0.39
    )});
    0.37
    étit
    0.37
    ButterKnife
    0.36
     dout
    0.36
    ]]);
    0.36
    '}';
    0.35
    "));
    
    0.35
     "));
    0.34
    Act Density 0.331%

    No Known Activations