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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ON
    1.41
     that
    1.28
    F
    1.27
    O
    1.20
    J
    1.20
    OV
    1.18
    Z
    1.18
    ET
    1.16
    R
    1.14
    OJ
    1.13
    POSITIVE LOGITS
    f
    1.53
    is
    1.51
    as
    1.30
    i
    1.25
    िया
    1.23
    ку
    1.20
    ات
    1.19
    ра
    1.16
    h
    1.16
    ی
    1.15
    Act Density 0.000%

    No Known Activations