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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    h
    1.29
     to
    1.22
     all
    1.18
     an
    1.15
     be
    1.13
    ,
    1.13
    /
    1.13
     as
    1.12
     up
    1.10
    ;
    1.09
    POSITIVE LOGITS
    ۔
    1.28
    мся
    1.27
    قة
    1.20
    д
    1.16
    ла
    1.13
    м
    1.11
    к
    1.06
    は
    1.06
    드가
    1.05
    درا
    1.01
    Act Density 0.000%

    No Known Activations