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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    狷
    -0.08
    撷
    -0.07
    rogram
    -0.07
     laser
    -0.07
    iber
    -0.07
    referrer
    -0.07
    不经意
    -0.07
    |↵↵
    -0.07
    Ever
    -0.06
    .setContent
    -0.06
    POSITIVE LOGITS
     seat
    0.09
     City
    0.08
    	best
    0.08
    私も
    0.07
    .languages
    0.07
    Hair
    0.07
    、「
    0.07
     Python
    0.07
    エ
    0.07
    Tiny
    0.07
    Act Density 0.002%

    No Known Activations