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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    思考
    0.37
     שלי
    0.37
    運用
    0.35
    ష్
    0.35
    grapes
    0.35
    ผู้ชม
    0.35
    ドキ
    0.35
    লিন
    0.35
    ᴼ
    0.35
    ೋತಿ
    0.34
    POSITIVE LOGITS
     authors
    0.53
     Reg
    0.45
     作者
    0.42
    Reg
    0.42
     Authors
    0.42
    rega
    0.42
    reg
    0.40
     writers
    0.40
    authors
    0.39
     الرج
    0.39
    Act Density 0.012%

    No Known Activations