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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    人に
    -0.07
    �
    -0.07
    iw
    -0.07
    /pol
    -0.07
    Documentation
    -0.07
    _Pro
    -0.07
    𝕣
    -0.07
    _${
    -0.06
     Were
    -0.06
    しっ
    -0.06
    POSITIVE LOGITS
    的声音
    0.07
     Catalog
    0.07
    .Usage
    0.07
    abei
    0.07
    名单
    0.07
     Marriage
    0.07
    水利工程
    0.07
     Habit
    0.07
    conti
    0.06
     TIMESTAMP
    0.06
    Act Density 0.008%

    No Known Activations