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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tuổi
    -0.07
    (COLOR
    -0.07
    nant
    -0.07
     giấc
    -0.07
     return
    -0.07
     fiscal
    -0.07
     proporcion
    -0.06
     come
    -0.06
    שפע
    -0.06
    .sender
    -0.06
    POSITIVE LOGITS
     debate
    0.10
     debated
    0.09
    钹
    0.09
     debates
    0.08
    脒
    0.08
    大家都
    0.08
    薢
    0.07
    辩
    0.07
    美术
    0.07
    用户名
    0.07
    Act Density 0.005%

    No Known Activations