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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     soar
    -0.07
    詳
    -0.07
    -------------</
    -0.07
    乐队
    -0.06
     ct
    -0.06
    醒了
    -0.06
    仅供
    -0.06
    �
    -0.06
    포
    -0.06
    auses
    -0.06
    POSITIVE LOGITS
     UB
    0.08
     recib
    0.07
    𥔲
    0.07
    (stat
    0.07
    引进
    0.07
     hod
    0.07
    _sampling
    0.07
    categorie
    0.07
     etwa
    0.07
     institutes
    0.07
    Act Density 0.013%

    No Known Activations