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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    要
    1.77
    のは
    1.70
    an
    1.66
    t
    1.62
    ti
    1.56
    igen
    1.52
    n
    1.38
    mmss
    1.38
    रन
    1.37
    anen
    1.34
    POSITIVE LOGITS
     ока
    2.02
     voir
    1.91
    atthaya
    1.90
     однако
    1.89
     उन्‍ह
    1.86
     leakage
    1.79
     folly
    1.78
    ,]
    1.77
     forgo
    1.76
     implique
    1.74
    Act Density 0.001%

    No Known Activations