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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    裂
    -0.07
    orption
    -0.07
    ater
    -0.07
    ?',
    -0.06
     uint
    -0.06
    超
    -0.06
    -building
    -0.06
    物品
    -0.06
    med
    -0.06
    疫情期间
    -0.06
    POSITIVE LOGITS
    Party
    0.07
    🌀
    0.07
    实现
    0.07
    PM
    0.07
    .AppendFormat
    0.07
     yup
    0.07
     chân
    0.07
    挽
    0.07
    _ORIGIN
    0.07
    \Schema
    0.06
    Act Density 0.058%

    No Known Activations