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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ب
    1.59
    ク
    1.38
    ین
    1.34
    بی
    1.34
    ات
    1.32
    ی
    1.30
    𝘀
    1.26
    ル
    1.24
    치
    1.24
    와의
    1.23
    POSITIVE LOGITS
     I
    1.31
     i
    1.21
    S
    1.20
    C
    1.18
     M
    1.15
     $
    1.13
    M
    1.13
     A
    1.12
    L
    1.12
    D
    1.11
    Act Density 0.000%

    No Known Activations