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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    zs
    -0.07
    bidden
    -0.07
     yargı
    -0.07
    inion
    -0.07
     CONST
    -0.07
     harbour
    -0.07
    bert
    -0.06
    火烧
    -0.06
    ushi
    -0.06
    stops
    -0.06
    POSITIVE LOGITS
    片区
    0.08
     הג
    0.07
     stranded
    0.07
    .session
    0.07
    প
    0.07
     (++
    0.07
     breakout
    0.07
     매
    0.07
     الر
    0.07
    돤
    0.07
    Act Density 0.028%

    No Known Activations