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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    弸
    -0.06
    𫖯
    -0.06
     Browser
    -0.06
     Spot
    -0.06
     appears
    -0.06
     repeats
    -0.06
     Unexpected
    -0.06
     XCT
    -0.06
    -margin
    -0.06
    心脏
    -0.06
    POSITIVE LOGITS
    \models
    0.08
    (lua
    0.07
    一家人
    0.07
    Rua
    0.07
     groom
    0.07
    的到来
    0.07
    unteers
    0.07
    的进步
    0.07
    anco
    0.07
     marrying
    0.07
    Act Density 0.044%

    No Known Activations