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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ("{
    -0.07
     tailored
    -0.07
    localctx
    -0.07
    关联
    -0.06
    clé
    -0.06
    Radio
    -0.06
    聊
    -0.06
    嵌
    -0.06
    瓯
    -0.06
    ublished
    -0.06
    POSITIVE LOGITS
    剧院
    0.07
    .trailing
    0.06
    室内
    0.06
    מרי
    0.06
    ⇞
    0.06
     skins
    0.06
    ⓕ
    0.06
    OGRAPH
    0.06
    能在
    0.06
    etrics
    0.06
    Act Density 0.009%

    No Known Activations