INDEX
    Explanations

    references to characters and their relationships in narrative contexts

    New Auto-Interp
    Negative Logits
    ê¶ģ
    -0.15
     gsi
    -0.14
    丸
    -0.14
    åĦĢ
    -0.14
    lli
    -0.14
    .dsl
    -0.14
    etine
    -0.13
    ElementsBy
    -0.13
    ubb
    -0.13
    anz
    -0.13
    POSITIVE LOGITS
    οÏħÏĤ
    0.16
    ythe
    0.14
     succ
    0.13
     Succ
    0.13
    bert
    0.13
    OKIE
    0.13
     plat
    0.12
    ä½ĵèĤ²
    0.12
    å®Ĺ
    0.12
    ffect
    0.12
    Act Density 0.001%

    No Known Activations