INDEX
    Explanations

    activities or hobbies that people enjoy

    expressions of enjoyment and activities related to personal interests

    New Auto-Interp
    Negative Logits
     Emin
    -0.70
    elled
    -0.69
    ilion
    -0.69
    ensus
    -0.69
    aye
    -0.68
    pload
    -0.67
    Already
    -0.66
    trak
    -0.66
     sshd
    -0.65
    wark
    -0.64
    POSITIVE LOGITS
     metaphors
    0.98
     acron
    0.93
     weddings
    0.92
     stuff
    0.88
     dudes
    0.87
     RPGs
    0.85
     desserts
    0.84
     hugs
    0.84
     gadgets
    0.83
     things
    0.83
    Act Density 0.702%

    No Known Activations