Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Having
    -2.41
    Another
    -2.23
    Putting
    -2.06
    Would
    -2.05
    Because
    -2.05
    gucig
    -1.98
    When
    -1.98
    Perhaps
    -1.95
    ･･
    -1.95
     壓
    -1.94
    POSITIVE LOGITS
     beş
    1.91
    ೢ
    1.76
    );
    1.73
     برخی
    1.73
     ),
    1.73
     Then
    1.72
     Now
    1.69
    ]
    1.68
     本体
    1.63
     So
    1.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.