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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     defend
    -0.07
     Overse
    -0.07
     intern
    -0.07
    inous
    -0.06
    morgan
    -0.06
    ,date
    -0.06
    征战
    -0.06
    ęb
    -0.06
    URIComponent
    -0.06
     stun
    -0.06
    POSITIVE LOGITS
    CPF
    0.07
    .rd
    0.07
     Notíc
    0.07
     требова
    0.07
    汉堡
    0.07
    ixed
    0.07
    רפואה
    0.07
     rng
    0.06
     rẻ
    0.06
    픽
    0.06
    Act Density 0.119%

    No Known Activations