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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     чаще
    0.40
     выбра
    0.40
    嫐
    0.40
     вики
    0.39
     escolh
    0.38
    んじゃない
    0.38
    朔
    0.37
    excited
    0.37
    жете
    0.37
    耐心
    0.37
    POSITIVE LOGITS
     pursuant
    0.40
     solely
    0.39
     Conditions
    0.38
    :,
    0.38
     する
    0.37
                   
    0.37
    :.
    0.37
    昀
    0.37
    Friday
    0.36
     Thursday
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.