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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Forbidden
    -0.80
    oppable
    -0.70
    ¥ŀ
    -0.63
     barric
    -0.61
     statutory
    -0.61
    glers
    -0.59
    ataka
    -0.59
     McCabe
    -0.58
     sights
    -0.58
    tarian
    -0.58
    POSITIVE LOGITS
    peak
    0.78
     LEVEL
    0.66
    tumblr
    0.65
    ortment
    0.65
     Improvement
    0.64
    Discussion
    0.63
    hyde
    0.62
    yip
    0.60
    hof
    0.60
    xual
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.