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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sometime
    -0.08
    🥵
    -0.08
     maximal
    -0.07
    .↵↵↵↵↵↵↵↵↵↵↵↵
    -0.07
     תפ
    -0.07
     learning
    -0.07
     Advice
    -0.07
    חלט
    -0.07
     meals
    -0.06
    震慑
    -0.06
    POSITIVE LOGITS
    ensor
    0.07
     processor
    0.07
    轮
    0.07
    𝐠
    0.07
    Pt
    0.07
    鱼
    0.07
    priv
    0.06
    丝
    0.06
    (ht
    0.06
     leather
    0.06
    Act Density 0.049%

    No Known Activations