INDEX
    Explanations

    movie reviews

    New Auto-Interp
    Negative Logits
    .prompt
    -0.08
    Lease
    -0.08
    ecan
    -0.08
    Approval
    -0.08
    /start
    -0.08
    -0.08
     leases
    -0.08
     roommates
    -0.07
    _today
    -0.07
     Clemson
    -0.07
    POSITIVE LOGITS
     nerv
    0.10
     parody
    0.10
     reminiscent
    0.10
     stylist
    0.10
     등장
    0.09
     pacing
    0.09
     homage
    0.09
     clichés
    0.09
     awkward
    0.09
     gimm
    0.09
    Act Density 0.299%

    No Known Activations