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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     commemorate
    -0.08
     spends
    -0.07
     deluxe
    -0.07
     Spare
    -0.07
     component
    -0.07
    精致
    -0.07
    🎻
    -0.07
    栖
    -0.06
    .title
    -0.06
     FUNC
    -0.06
    POSITIVE LOGITS
    icios
    0.06
    ursday
    0.06
     opr
    0.06
     exhibited
    0.06
    绿豆
    0.06
     Blocking
    0.06
    되면
    0.06
     seeded
    0.06
     rejected
    0.06
     omdat
    0.06
    Act Density 0.009%

    No Known Activations