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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    疖
    -0.07
    جهاد
    -0.07
    产业升级
    -0.07
    屑
    -0.07
    松弛
    -0.07
     suddenly
    -0.07
     easiest
    -0.06
    INFO
    -0.06
    uele
    -0.06
     Faster
    -0.06
    POSITIVE LOGITS
    .models
    0.07
    压制
    0.07
    rolling
    0.07
    -writing
    0.07
     Colt
    0.07
     anim
    0.07
     Kentucky
    0.06
     LDS
    0.06
    กา
    0.06
     tattoo
    0.06
    Act Density 0.003%

    No Known Activations