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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OU
    -0.84
    uously
    -0.81
    IST
    -0.81
    ually
    -0.75
    Stew
    -0.72
    urg
    -0.70
    Pie
    -0.69
    lamm
    -0.68
    Ñĭ
    -0.67
    ISO
    -0.66
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.77
    xit
    0.73
     proport
    0.73
     pse
    0.71
     predec
    0.65
    è¦ļéĨĴ
    0.64
     cov
    0.63
    ategory
    0.62
    theless
    0.62
    iership
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.