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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fourni
    0.52
     peuple
    0.52
     dola
    0.50
     alti
    0.50
     russian
    0.48
     camere
    0.48
     plików
    0.48
    :::
    0.47
     sadde
    0.47
     ł
    0.47
    POSITIVE LOGITS
    ра
    0.64
    रा
    0.58
    ка
    0.57
    𝑎
    0.52
    ется
    0.51
    ч
    0.51
    ंड
    0.50
    а
    0.50
    ного
    0.49
    ع
    0.49
    Act Density 0.000%

    No Known Activations