INDEX
    Explanations

    expressions of urgency related to fundraising or support

    New Auto-Interp
    Negative Logits
     –,
    -0.88
    */;
    -0.87
    ]';
    -0.82
    -0.80
    </caption>
    -0.80
    ")));
    
    -0.74
    ')));
    -0.72
     bezeichneter
    -0.71
    />";
    -0.70
    !")
    
    -0.69
    POSITIVE LOGITS
     #
    2.28
     @
    2.05
    #
    1.73
    @
    1.48
     \#
    1.35
    .#
    1.29
    -#
    1.27
    .@
    1.27
     (@
    1.25
    ,@
    1.22
    Act Density 0.204%

    No Known Activations