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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     disappointment
    -0.07
    igte
    -0.07
     wurden
    -0.07
    чет
    -0.06
     الخيار
    -0.06
    ļ
    -0.06
     If
    -0.06
     et
    -0.06
     يعد
    -0.06
     so
    -0.06
    POSITIVE LOGITS
    大城市
    0.08
    (annotation
    0.08
    /{$
    0.08
    朝阳
    0.07
     hovering
    0.07
    -Apr
    0.07
     América
    0.07
    个小
    0.06
     surviv
    0.06
    遍布
    0.06
    Act Density 0.009%

    No Known Activations