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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     И
    0.84
     Этот
    0.81
     этого
    0.80
     был
    0.79
     этот
    0.78
     тот
    0.78
     пыта
    0.76
    ногие
    0.75
     было
    0.74
     еще
    0.74
    POSITIVE LOGITS
     semplici
    0.82
    ricular
    0.76
     Ashby
    0.75
     sistemat
    0.75
    profits
    0.73
    EVENTS
    0.73
     stai
    0.72
    .
    0.72
    ামো
    0.71
     finan
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.