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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ignore
    -0.07
    مرض
    -0.07
     Might
    -0.07
    不予
    -0.07
    re
    -0.07
     fireplace
    -0.07
    中最
    -0.07
     embrace
    -0.07
    가
    -0.07
     scoff
    -0.06
    POSITIVE LOGITS
     ►
    0.07
     UT
    0.07
    STAR
    0.07
    辫
    0.07
    (LL
    0.07
     visionary
    0.07
     lateral
    0.07
    产业
    0.06
    ∼
    0.06
    ጃ
    0.06
    Act Density 0.011%

    No Known Activations