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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <bos>
    1.98
    ot
    1.52
    ч
    1.50
     বলিয়া
    1.49
    }^\
    1.47
    पछि
    1.47
    }.
    1.46
    कीय
    1.46
    ================
    1.45
    ্যান্ড
    1.42
    POSITIVE LOGITS
    ately
    2.03
    िक
    1.96
    い
    1.90
    িগ্ন
    1.89
     suppose
    1.87
    ciences
    1.79
    teg
    1.78
    此同时
    1.76
     Hỏi
    1.76
    𝐧
    1.75
    Act Density 0.001%

    No Known Activations