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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ("***
    -0.07
    ivial
    -0.07
     separating
    -0.07
    זה
    -0.07
    jt
    -0.07
    入学
    -0.07
     register
    -0.06
    happy
    -0.06
    (/
    -0.06
    metadata
    -0.06
    POSITIVE LOGITS
    Ⲟ
    0.07
    蹩
    0.07
    뺏
    0.06
    �
    0.06
     bargain
    0.06
    歅
    0.06
     рестор
    0.06
    渲
    0.06
    ographers
    0.06
    햤
    0.06
    Act Density 0.032%

    No Known Activations