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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     horrors
    0.72
     Bên
    0.69
     mock
    0.68
     Anonymous
    0.66
     veřej
    0.66
     Amid
    0.65
    mock
    0.63
     horrifying
    0.63
    階
    0.63
     renaming
    0.63
    POSITIVE LOGITS
     decreased
    1.37
     quicker
    1.36
     increased
    1.35
     slower
    1.31
     faster
    1.29
     fewer
    1.28
     denser
    1.24
     less
    1.24
    更快
    1.23
     smoother
    1.23
    Act Density 2.465%

    No Known Activations