INDEX
    Explanations

    dialogues and interactions between characters in a narrative

    New Auto-Interp
    Negative Logits
     Trit
    -0.15
    efeller
    -0.15
    arro
    -0.15
    öl
    -0.15
    eil
    -0.14
    zia
    -0.13
    hiba
    -0.13
    tt
    -0.13
    _attached
    -0.13
     tri
    -0.13
    POSITIVE LOGITS
    سر
    0.15
    ãĤ»
    0.15
    adera
    0.14
    ä¹ĭä¸Ģ
    0.14
    enga
    0.14
    ãĥ¼ãĥģ
    0.14
    INET
    0.14
    IJľ
    0.14
    enschaft
    0.14
    737
    0.14
    Act Density 0.530%

    No Known Activations