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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     liberté
    -0.08
    *angstrom
    -0.08
    否則
    -0.07
    -performance
    -0.07
     TreeSet
    -0.07
     EVT
    -0.07
    думать
    -0.07
    坋
    -0.07
    滘
    -0.07
    فن
    -0.07
    POSITIVE LOGITS
     bug
    0.08
    的关系
    0.07
     civic
    0.07
     Wo
    0.07
     outlined
    0.07
    分期
    0.07
     geme
    0.06
     scholarly
    0.06
    率
    0.06
    .take
    0.06
    Act Density 0.001%

    No Known Activations