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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ends
    -0.07
    .bc
    -0.07
    ǣ
    -0.07
    uyên
    -0.07
    riminal
    -0.07
     spoon
    -0.07
    睢
    -0.07
    _BLK
    -0.07
     tape
    -0.07
     poniew
    -0.06
    POSITIVE LOGITS
    下单
    0.07
     meds
    0.07
    �
    0.07
    Plus
    0.06
    Jeff
    0.06
    的游戏
    0.06
     Dive
    0.06
    เปล
    0.06
     suggesting
    0.06
    iniz
    0.06
    Act Density 0.025%

    No Known Activations