INDEX
    Explanations

    references to the subject "she" in various contexts

    New Auto-Interp
    Negative Logits
    utenberg
    -0.16
    ship
    -0.16
    noc
    -0.16
    ãĥĥ
    -0.15
    าà¸į
    -0.15
    assen
    -0.15
     Widow
    -0.15
    thic
    -0.14
    atis
    -0.14
    ses
    -0.14
    POSITIVE LOGITS
    ppard
    0.20
    pherd
    0.19
    ffield
    0.19
    ikh
    0.18
    ields
    0.18
    -même
    0.17
     Husband
    0.16
    elden
    0.16
    arer
    0.15
    pher
    0.15
    Act Density 0.085%

    No Known Activations