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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     plung
    -0.07
    沧
    -0.07
     соглас
    -0.06
    的消息
    -0.06
     IMM
    -0.06
     poking
    -0.06
    つけ
    -0.06
    asca
    -0.06
     Paige
    -0.06
    ysz
    -0.06
    POSITIVE LOGITS
    网
    0.08
    变
    0.07
    網
    0.07
    机制
    0.07
    lit
    0.07
    群
    0.07
     ("
    0.07
    housing
    0.06
    🌋
    0.06
    finite
    0.06
    Act Density 0.004%

    No Known Activations