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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     qualified
    -0.09
    グラ
    -0.07
     paso
    -0.07
     POSITION
    -0.07
    .program
    -0.06
    kke
    -0.06
    火力
    -0.06
    黄瓜
    -0.06
     brushing
    -0.06
    מרק
    -0.06
    POSITIVE LOGITS
     eviction
    0.07
     geschichten
    0.07
    怂
    0.07
     bezpo
    0.07
    вест
    0.07
     Hardcover
    0.06
     provides
    0.06
    	RT
    0.06
    ゔ
    0.06
    𐱅
    0.06
    Act Density 0.000%

    No Known Activations