INDEX
    Explanations

    light, glow, and illumination

    New Auto-Interp
    Negative Logits
    🌪
    0.42
     unordered
    0.42
    0.41
    0.39
    0.37
     سكس
    0.36
     deque
    0.35
    0.35
    lego
    0.35
    쫀득
    0.35
    POSITIVE LOGITS
     illumination
    2.80
     lighting
    2.73
     iluminación
    2.59
     ilumin
    2.55
     lights
    2.53
     illuminate
    2.53
     illumin
    2.48
     illuminated
    2.47
     illuminating
    2.44
    照明
    2.42
    Act Density 0.240%

    No Known Activations