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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Kat
    -0.07
    Container
    -0.07
     zoning
    -0.07
    authorized
    -0.07
    draw
    -0.06
    河水
    -0.06
     crim
    -0.06
    .Function
    -0.06
     detained
    -0.06
    자격
    -0.06
    POSITIVE LOGITS
    .Att
    0.07
    座椅
    0.07
     Odds
    0.07
    (options
    0.06
    ướng
    0.06
     לכן
    0.06
    총
    0.06
    (cnt
    0.06
    很多朋友
    0.06
    (::
    0.06
    Act Density 0.201%

    No Known Activations