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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ina
    1.25
    2
    1.23
    3
    1.16
    nde
    1.12
    ahun
    1.07
    imde
    1.06
    imi
    1.03
     exclamation
    1.03
    im
    1.02
    ige
    1.02
    POSITIVE LOGITS
    而是
    1.23
     बल्कि
    1.16
    🙅
    1.09
     anymore
    1.05
     Nor
    1.00
     meisten
    1.00
    大多數
    0.97
     بلکه
    0.94
    Nor
    0.91
     nor
    0.91
    Act Density 2.677%

    No Known Activations