INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    :✨
    -0.62
    parti
    -0.60
    StoryboardSegue
    -0.59
    pompa
    -0.55
    festa
    -0.55
    ofy
    -0.54
     Fais
    -0.54
    menti
    -0.54
    cozy
    -0.54
    DotNetBar
    -0.54
    POSITIVE LOGITS
    red
    2.36
    RED
    1.81
     red
    1.66
    Red
    1.52
    reds
    1.43
     Red
    1.37
     RED
    1.32
    1.16
    1.09
     reds
    1.08
    Act Density 0.014%

    No Known Activations