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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isu
    1.04
    ets
    1.03
     forma
    1.01
     rope
    1.00
     sari
    0.99
    时候
    0.98
     en
    0.97
    HAN
    0.97
    else
    0.96
    ى
    0.94
    POSITIVE LOGITS
     conteú
    1.39
     précédemment
    1.34
    ה
    1.33
    yfik
    1.27
     Sự
    1.24
    ați
    1.23
    謡
    1.23
    IBLE
    1.23
    ciones
    1.21
    原因
    1.21
    Act Density 0.000%

    No Known Activations