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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pParent
    -0.30
    oval
    -0.28
     dereg
    -0.28
    _PKG
    -0.25
     Patt
    -0.25
    ows
    -0.24
    ä¸įè§ģ
    -0.24
    åŁ¹
    -0.24
    èĬ±å¼Ģ
    -0.23
    enter
    -0.23
    POSITIVE LOGITS
    æľĢä½³
    0.29
     discriminator
    0.28
    hani
    0.28
    éĹ®ä»ĸ
    0.26
    æľĢå¿«çļĦ
    0.25
    åIJĪä½ľä¼Ļä¼´
    0.24
    ç«ŀäºī对æīĭ
    0.24
    ãģ¿
    0.24
    tokenId
    0.24
     Griffin
    0.24
    Act Density 0.001%

    No Known Activations

    This feature has no known activations.