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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    罹
    -0.07
    tea
    -0.07
     spiel
    -0.07
     curl
    -0.07
     blinked
    -0.07
     culp
    -0.07
    _mp
    -0.06
     harms
    -0.06
    了一口
    -0.06
    Ⱑ
    -0.06
    POSITIVE LOGITS
    agle
    0.07
    оборот
    0.07
    (pred
    0.07
    前置
    0.07
    总理
    0.07
    主观
    0.07
    shake
    0.07
    avigator
    0.07
    隐形
    0.07
    ág
    0.07
    Act Density 0.233%

    No Known Activations