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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ủy
    -0.07
     cơ
    -0.07
    تباع
    -0.07
    כי
    -0.06
     pik
    -0.06
    监督检查
    -0.06
    采纳
    -0.06
    俸
    -0.06
    ừ
    -0.06
    恤
    -0.06
    POSITIVE LOGITS
    එ
    0.08
    伤亡
    0.07
    เผ
    0.07
    (one
    0.07
    ➾
    0.07
    ngr
    0.07
    Temporal
    0.06
    ("!
    0.06
    (movie
    0.06
    <LM
    0.06
    Act Density 0.001%

    No Known Activations