INDEX
    Explanations

    dialogue or quotes that indicate someone's opinion or statement

    New Auto-Interp
    Negative Logits
    Ease
    -0.15
    ÃĹ↵↵
    -0.13
    λά
    -0.13
     kred
    -0.13
    uro
    -0.13
    avo
    -0.12
     ÑĤеÑĩ
    -0.12
    lie
    -0.12
    تÙĨ
    -0.12
    ander
    -0.12
    POSITIVE LOGITS
     one
    0.38
     said
    0.22
    ä¸Ģ个
    0.21
     má»Ļt
    0.20
     an
    0.19
     eines
    0.19
     a
    0.19
    ä¸ĢåĢĭ
    0.19
     longtime
    0.19
     ÛĮÚ©ÛĮ
    0.18
    Act Density 0.039%

    No Known Activations