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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    line
    -0.07
     Expedition
    -0.07
     Diagnosis
    -0.07
    饹
    -0.07
    部署
    -0.06
    […
    -0.06
    mis
    -0.06
    isu
    -0.06
    還是
    -0.06
    ﻨ
    -0.06
    POSITIVE LOGITS
    0.07
     (%)
    0.07
    琫
    0.07
    חובה
    0.07
    (IB
    0.07
     factories
    0.07
    /colors
    0.07
    交通大学
    0.07
    ꧈
    0.07
     tablespoon
    0.06
    Act Density 0.012%

    No Known Activations