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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     shop
    -0.08
     shops
    -0.08
    省级
    -0.07
    EDGE
    -0.07
     scholarly
    -0.07
    -0.07
     Provider
    -0.07
    SIDE
    -0.06
     الا
    -0.06
     sư
    -0.06
    POSITIVE LOGITS
    ￂ
    0.07
    seven
    0.07
    昒
    0.06
    ван
    0.06
    叨
    0.06
     Alerts
    0.06
    𝙇
    0.06
    렐
    0.06
    짖
    0.06
    śli
    0.06
    Act Density 0.016%

    No Known Activations