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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dân
    -0.06
    participant
    -0.06
     Birds
    -0.06
    赃
    -0.06
     ail
    -0.06
    忙
    -0.06
     advises
    -0.06
     '{
    -0.06
    汊
    -0.05
    的话题
    -0.05
    POSITIVE LOGITS
    인데
    0.08
    :.
    0.07
    していて
    0.07
     induced
    0.07
    が多く
    0.07
    _variance
    0.07
     fixed
    0.07
    やっぱり
    0.07
    gra
    0.07
     depicting
    0.07
    Act Density 0.005%

    No Known Activations