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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    connexion
    -0.07
    佻
    -0.07
    拎
    -0.07
    좔
    -0.07
    🚖
    -0.07
    跐
    -0.07
     fırs
    -0.07
    �
    -0.07
    停下
    -0.07
    )dealloc
    -0.07
    POSITIVE LOGITS
    干部职工
    0.07
    有关部门
    0.07
    method
    0.07
     PM
    0.07
    ѣ
    0.07
    顯示
    0.07
    .ur
    0.07
     temporal
    0.06
     prisoners
    0.06
     iterable
    0.06
    Act Density 0.005%

    No Known Activations