INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pleasantly
    0.88
     narrower
    0.85
     pleasant
    0.82
     اچھی
    0.82
     piccoli
    0.81
     bistro
    0.81
     cabaret
    0.79
     sweeter
    0.77
    0.77
    িদ্ধ
    0.76
    POSITIVE LOGITS
     gigantic
    3.15
     massive
    2.97
     enormous
    2.92
     colossal
    2.84
     huge
    2.83
     огром
    2.80
     enormes
    2.60
     Huge
    2.58
     giant
    2.57
     enorme
    2.57
    Act Density 1.333%

    No Known Activations