INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     tyrannical
    0.55
     गिरफ्त
    0.55
    0.54
     spoof
    0.53
     sexist
    0.53
     macho
    0.52
     dictatorship
    0.52
     punitive
    0.51
     gangster
    0.51
     SWAT
    0.51
    POSITIVE LOGITS
     wildflowers
    1.33
     sunflowers
    1.29
     sunsets
    1.27
     flowers
    1.22
     sunrise
    1.16
     wildflower
    1.13
     sunlight
    1.13
     sunset
    1.10
     sunflower
    1.09
     trees
    1.08
    Act Density 0.050%

    No Known Activations