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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     seep
    1.62
     bőr
    1.62
     تعالى
    1.52
    𝓸
    1.52
     propriétés
    1.51
    𝓼
    1.50
     pytest
    1.49
     detener
    1.48
    𝘪
    1.47
    𝓷
    1.47
    POSITIVE LOGITS
    neat
    1.54
    treasure
    1.54
    не
    1.31
    ﻪ
    1.31
    이
    1.30
    mild
    1.29
    étranger
    1.27
    년간
    1.26
    now
    1.26
    Jaw
    1.25
    Act Density 0.001%

    No Known Activations