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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Vet
    -0.07
     bruises
    -0.07
    {_
    -0.07
    iswa
    -0.07
    咎
    -0.07
    扫描
    -0.07
    (ai
    -0.06
    的女儿
    -0.06
    钻
    -0.06
    jr
    -0.06
    POSITIVE LOGITS
    )',↵
    0.08
    有很多种
    0.07
    עונ
    0.07
    -dropdown
    0.07
    ReceiveMemoryWarning
    0.07
    空气
    0.07
    �
    0.07
     WAV
    0.07
    )});↵
    0.07
     עש
    0.07
    Act Density 0.005%

    No Known Activations