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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bbe
    -0.07
     Dre
    -0.07
    Krist
    -0.07
    侔
    -0.07
     intr
    -0.06
    _wrapper
    -0.06
     denominator
    -0.06
    衬
    -0.06
     infer
    -0.06
     Sor
    -0.06
    POSITIVE LOGITS
    用微信
    0.08
     concentrating
    0.07
    ⠇
    0.07
     Loading
    0.07
     weighting
    0.07
     إذ
    0.07
    }',
    0.07
    姿势
    0.07
    主力
    0.07
     ###↵
    0.07
    Act Density 0.001%

    No Known Activations