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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    conservancy
    -0.66
    bour
    -0.66
    uana
    -0.65
     WATCH
    -0.63
    haw
    -0.63
     Junction
    -0.62
     Offense
    -0.62
     Lack
    -0.62
    ino
    -0.61
    bors
    -0.61
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    0.85
    byss
    0.81
    æ©Ł
    0.72
    rogens
    0.72
    å§
    0.71
    metry
    0.69
    ateurs
    0.69
    ĸļ
    0.68
    liv
    0.66
    ACE
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.