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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    0.57
    Сере
    0.47
     języ
    0.46
    ’
    0.44
     quét
    0.44
    :^(
    0.44
     wording
    0.43
     made
    0.43
     suited
    0.43
     worded
    0.43
    POSITIVE LOGITS
    ن
    0.49
    }$)
    0.46
    ات
    0.46
    കാല
    0.45
    тт
    0.44
    নাথ
    0.44
    ب
    0.44
    ه
    0.42
    arctica
    0.42
    不断的
    0.42
    Act Density 0.004%

    No Known Activations