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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     daycare
    1.46
     housework
    1.39
     patriotism
    1.35
     mensen
    1.32
     возле
    1.31
     žena
    1.30
     restoran
    1.29
     adoration
    1.29
     wages
    1.28
     homestead
    1.28
    POSITIVE LOGITS
    F
    1.21
    R
    1.17
     (
    1.16
    PhysRev
    1.16
    B
    1.16
    V
    1.15
    （
    1.14
     outperforms
    1.09
     optimized
    1.08
    optimized
    1.08
    Act Density 0.828%

    No Known Activations