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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     liken
    -0.08
    馒
    -0.07
     Crane
    -0.07
    schemas
    -0.07
    rawer
    -0.07
    包子
    -0.07
    一封信
    -0.07
     билет
    -0.07
     terrified
    -0.07
     unheard
    -0.06
    POSITIVE LOGITS
     '))↵
    0.07
     الجه
    0.07
     &);↵
    0.06
     wij
    0.06
     EN
    0.06
    𝙻
    0.06
    .');↵↵
    0.06
     structural
    0.06
    _;↵↵
    0.06
    開發
    0.06
    Act Density 0.033%

    No Known Activations