INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.82
     ſeveral
    -0.76
     Theſe
    -0.75
     houſe
    -0.72
     himſelf
    -0.69
     Efq
    -0.66
     Jefus
    -0.64
     whoſe
    -0.63
     tranſ
    -0.61
     ſhe
    -0.61
    POSITIVE LOGITS
    ]$.
    0.74
    ");
    0.71
    );
    0.68
    )\
    0.68
    ]$
    0.68
    ]));
    0.68
    ].
    0.66
    ));
    0.66
    ]);
    0.65
    ];
    0.64
    Act Density 1.538%

    No Known Activations