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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \Action
    -0.07
     HOWEVER
    -0.07
    叶修
    -0.07
     teen
    -0.07
    ድ
    -0.06
    ice
    -0.06
     Portions
    -0.06
     Without
    -0.06
    аться
    -0.06
    ighting
    -0.06
    POSITIVE LOGITS
     dal
    0.07
     tense
    0.07
    坦克
    0.07
     לקנות
    0.07
    稞
    0.06
    ༜
    0.06
     lk
    0.06
    .EntityFramework
    0.06
     ipad
    0.06
     wz
    0.06
    Act Density 0.154%

    No Known Activations