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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    忆
    -0.08
    Петер
    -0.07
    кл
    -0.07
     lifelong
    -0.07
     delet
    -0.07
    آخر
    -0.07
    筋
    -0.07
     {?>↵
    -0.07
     diagn
    -0.07
    ∷
    -0.07
    POSITIVE LOGITS
     LoggerFactory
    0.07
    bilité
    0.07
     flashy
    0.07
     والح
    0.07
    卑
    0.07
    Party
    0.07
    工商局
    0.06
     arbitr
    0.06
     rush
    0.06
    _verbose
    0.06
    Act Density 0.003%

    No Known Activations