INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ة
    0.79
    ת
    0.79
    0.77
    0.76
    ش
    0.72
    ing
    0.71
    أ
    0.67
    ה
    0.66
    ه
    0.65
    O
    0.61
    POSITIVE LOGITS
     bali
    0.79
     Bali
    0.74
     ME
    0.57
     बाली
    0.55
    		
    0.55
     Ubud
    0.55
    in
    0.54
     były
    0.54
     Bache
    0.54
    Bali
    0.53
    Act Density 0.001%

    No Known Activations