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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    =date
    -0.08
     CLOCK
    -0.07
    ophage
    -0.07
    WORD
    -0.07
    HEAD
    -0.07
    ELCOME
    -0.07
     Illinois
    -0.07
    URRENCY
    -0.07
    感悟
    -0.07
    𬘩
    -0.07
    POSITIVE LOGITS
     @"\
    0.08
    卯
    0.07
    确切
    0.07
    uner
    0.07
    尬
    0.07
     undermining
    0.07
    >G
    0.07
    竞
    0.07
     reliably
    0.07
    ≪
    0.06
    Act Density 0.009%

    No Known Activations