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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     प्रश्‍
    0.50
    -​
    0.47
    ‑
    0.46
     prohibitions
    0.45
     ‘‘
    0.44
     insofar
    0.44
    particularly
    0.42
     apiece
    0.42
     प्रश्‍न
    0.42
    )–
    0.42
    POSITIVE LOGITS
    ");
    0.75
     {}",
    0.73
    ...");
    0.69
     {}
    0.68
     {}".
    0.68
     ...");
    0.67
     =====
    0.66
     ---
    0.66
     ");
    0.66
     TODO
    0.66
    Act Density 2.689%

    No Known Activations