INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     
    0.59
     B
    0.54
     D
    0.49
     la
    0.48
     della
    0.47
     de
    0.47
     the
    0.46
     L
    0.46
     C
    0.45
     M
    0.45
    POSITIVE LOGITS
    ING
    0.57
    ЛИ
    0.55
    Й
    0.55
    ר
    0.54
    בי
    0.49
    vykor
    0.49
    לי
    0.48
    이트
    0.48
     CLIENTI
    0.48
    ти
    0.48
    Act Density 0.288%

    No Known Activations