INDEX
    Explanations

    references to the name "Derek."

    New Auto-Interp
    Negative Logits
    WithOptions
    -0.16
     bul
    -0.15
    iferay
    -0.15
    verte
    -0.15
    illery
    -0.14
    /module
    -0.14
    omer
    -0.14
    onas
    -0.14
     mere
    -0.14
     Brew
    -0.14
    POSITIVE LOGITS
    ÑĥÑĩ
    0.14
    Pane
    0.14
    amedi
    0.14
     bloody
    0.14
    ocide
    0.14
    edar
    0.13
    ishi
    0.13
    owane
    0.13
    _NS
    0.13
    ovic
    0.13
    Act Density 0.005%

    No Known Activations