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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     or
    1.36
     или
    1.35
     either
    1.34
    或
    1.32
     أو
    1.30
    :
    1.27
    either
    1.24
     Either
    1.21
    หรือไม่
    1.19
     hoặc
    1.16
    POSITIVE LOGITS
     家具
    1.34
     寝
    1.29
     décide
    1.25
    1.25
    톄
    1.20
    तों
    1.19
     yönetim
    1.18
    궪
    1.17
     forgo
    1.17
     ziehen
    1.17
    Act Density 0.109%

    No Known Activations