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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ㅣ
    0.43
    ㅁ
    0.42
    攵
    0.42
     tombe
    0.39
     wont
    0.39
    érences
    0.39
     apl
    0.38
    seyside
    0.38
     fillet
    0.37
    っいて
    0.37
    POSITIVE LOGITS
     दैट
    0.46
     विद
    0.40
    That
    0.40
     که
    0.39
    Maybe
    0.38
    મ
    0.38
     wszel
    0.37
     that
    0.36
     That
    0.36
    }
    0.36
    Act Density 0.001%

    No Known Activations