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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sidel
    -0.08
    发生变化
    -0.07
    发展中
    -0.07
     intrigue
    -0.07
    ーシ
    -0.07
    取胜
    -0.07
     shipment
    -0.06
    ifa
    -0.06
    trust
    -0.06
    ophil
    -0.06
    POSITIVE LOGITS
     Rifle
    0.08
    Raise
    0.07
    ﭶ
    0.07
     והוא
    0.07
    骓
    0.07
     arrived
    0.06
    楼上
    0.06
     ale
    0.06
    Generally
    0.06
     forum
    0.06
    Act Density 0.012%

    No Known Activations