INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     cavern
    0.47
    t
    0.47
     Pompe
    0.45
     cave
    0.43
    ها
    0.43
    তীর্থ
    0.41
     open
    0.41
     belly
    0.40
     marble
    0.40
     amphithe
    0.40
    POSITIVE LOGITS
     Window
    0.74
    0.71
     window
    0.70
     jendela
    0.70
    0.70
    Window
    0.70
     windowsill
    0.69
     ventana
    0.68
     fenêtre
    0.68
     janela
    0.65
    Act Density 0.047%

    No Known Activations