INDEX
    Explanations

    references to 'face' and facial expressions in various contexts

    "face" and its context

    New Auto-Interp
    Negative Logits
    }));
    
    -0.98
    "]));
    -0.89
    )});
    -0.82
    })));
    -0.82
    ]));
    
    -0.81
    Datuak
    -0.81
    ")));
    
    -0.79
    neros
    -0.79
    קישורים
    -0.78
    LEGGI
    -0.76
    POSITIVE LOGITS
     Face
    1.61
     face
    1.59
     faces
    1.56
    face
    1.45
    Face
    1.44
     FACE
    1.41
     Faces
    1.37
    FACE
    1.31
    faces
    1.27
    Faces
    1.18
    Act Density 0.087%

    No Known Activations