INDEX
    Explanations

    specific personal information

    New Auto-Interp
    Negative Logits
    解説
    0.99
     explain
    0.94
    explanation
    0.94
     explanation
    0.93
     объяснить
    0.91
     explaining
    0.91
     explanations
    0.90
     explains
    0.84
     explicar
    0.83
     explicação
    0.83
    POSITIVE LOGITS
     information
    3.95
    information
    3.70
     Information
    3.57
    Information
    3.57
    信息
    3.29
    情報
    3.25
     información
    3.25
     informatie
    3.23
     정보
    3.20
     정보를
    3.14
    Act Density 0.594%

    No Known Activations