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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     urban
    -0.07
    .pixel
    -0.07
     büyü
    -0.07
    腒
    -0.07
    𓇼
    -0.07
    .storage
    -0.07
    אביב
    -0.07
     уровня
    -0.07
    İLİ
    -0.07
     אישי
    -0.07
    POSITIVE LOGITS
    俱
    0.07
    emann
    0.07
     deported
    0.07
    junction
    0.07
    蜂蜜
    0.06
    Desc
    0.06
    起诉
    0.06
    巡
    0.06
    Sampler
    0.06
     singular
    0.06
    Act Density 0.011%

    No Known Activations