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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .subject
    -0.07
    慣
    -0.07
     hovering
    -0.07
    锚
    -0.07
     Воз
    -0.06
     sider
    -0.06
     intervening
    -0.06
     Craft
    -0.06
     proverb
    -0.06
    失望
    -0.06
    POSITIVE LOGITS
    ação
    0.07
    lam
    0.07
    res
    0.07
     feu
    0.06
     Bordeaux
    0.06
    התנהגות
    0.06
    Descriptions
    0.06
     ра�
    0.06
    prod
    0.06
     Velvet
    0.06
    Act Density 0.008%

    No Known Activations