INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.07
    4:0.07
    5:0.06
    6:0.08
    7:0.07
    8:0.09
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     Maps
    -3.09
     Lighting
    -2.83
     shading
    -2.75
     Roads
    -2.74
     liner
    -2.68
     Architects
    -2.67
     Robotics
    -2.67
     Graphics
    -2.66
     Stretch
    -2.66
     Telesc
    -2.66
    POSITIVE LOGITS
    >>>>>>>>
    3.22
    aimon
    3.05
    ifax
    2.99
    itual
    2.89
    hon
    2.83
    aban
    2.81
    >>>>
    2.73
    emort
    2.69
    ét
    2.69
    2.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.