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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    opic
    -0.60
    HP
    -0.60
    Todd
    -0.59
     Kad
    -0.58
     debian
    -0.58
     distraction
    -0.58
    umers
    -0.58
    Percent
    -0.58
    ylan
    -0.57
    idal
    -0.57
    POSITIVE LOGITS
     tiss
    0.74
    ãĤ¨ãĥ«
    0.71
    ilitary
    0.70
    aughs
    0.68
    eatures
    0.68
    forth
    0.66
    angered
    0.64
    merce
    0.64
    è¦ļéĨĴ
    0.63
    æĸ¹
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.