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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Restaurant
    -0.07
    Copy
    -0.07
    公共
    -0.07
    content
    -0.07
    .Fields
    -0.07
    }↵↵
    -0.07
    ことに
    -0.07
    Fade
    -0.07
    )]↵↵
    -0.07
    加強
    -0.07
    POSITIVE LOGITS
     the
    0.08
    斧
    0.08
     and
    0.07
    的
    0.07
    lox
    0.07
     ux
    0.07
    凭什么
    0.07
    ẅ
    0.07
    ឧ
    0.06
    �
    0.06
    Act Density 0.014%

    No Known Activations