INDEX
    Explanations

    Code documentation

    The neuron activates on structural markup tokens—i.e. the bracketed labels and tag delimiters (like “[”, “/”, and tag names) that mark sections of the text.

    New Auto-Interp
    Negative Logits
     "=",
    -0.06
     CONSTANT
    -0.06
    ーテ
    -0.06
     Fans
    -0.06
    -0.06
    �인
    -0.06
    ือถ
    -0.06
     Tire
    -0.06
     assum
    -0.06
    -0.05
    POSITIVE LOGITS
     Ashley
    0.07
     PS
    0.07
     Programmer
    0.06
     Banana
    0.06
    PixelFormat
    0.06
     murderer
    0.06
    enz
    0.06
    education
    0.06
     prisoner
    0.06
    -highlight
    0.06
    Act Density 0.007%

    No Known Activations