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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Te
    -0.08
     Friend
    -0.07
     autonomous
    -0.07
     diplom
    -0.07
    万余
    -0.07
    将士
    -0.07
     constructing
    -0.07
    .pred
    -0.07
     Ros
    -0.06
     throttle
    -0.06
    POSITIVE LOGITS
    🏟
    0.08
    蹾
    0.08
     survived
    0.07
    传统文化
    0.07
    文化传播
    0.07
     yaşam
    0.07
     ()
↵
    0.07
     expectedResult
    0.06
    崇拜
    0.06
    лага
    0.06
    Act Density 0.003%

    No Known Activations