INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    PVC
    0.61
     LTS
    0.57
     PU
    0.56
     Puch
    0.56
    glass
    0.55
     LPS
    0.55
     transluc
    0.55
    ABS
    0.55
     Lumen
    0.54
     Singers
    0.54
    POSITIVE LOGITS
     gorilla
    1.11
     Gorilla
    1.09
     gorillas
    0.95
    Gor
    0.93
     gor
    0.90
    gor
    0.86
     Gor
    0.85
     strengthening
    0.76
     strengthened
    0.73
     Strengthening
    0.71
    Act Density 0.008%

    No Known Activations