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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ction
    1.62
    ointments
    1.53
    ytical
    1.37
    ties
    1.32
    le
    1.30
    stays
    1.24
    യ
    1.23
     Portman
    1.23
    жению
    1.21
    vartheta
    1.21
    POSITIVE LOGITS
    生素
    1.49
    ीन
    1.42
    ج
    1.32
    ்
    1.30
     thách
    1.26
    𝗮
    1.23
    ์
    1.22
    х
    1.22
    𝘁
    1.21
    ğı
    1.19
    Act Density 0.048%

    No Known Activations