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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Committees
    -0.07
    夫妇
    -0.07
     Hamm
    -0.07
    鸽
    -0.06
     Requests
    -0.06
     Datagram
    -0.06
     foss
    -0.06
     MONEY
    -0.06
    generator
    -0.06
     Beaver
    -0.06
    POSITIVE LOGITS
    ᐉ
    0.07
    🐜
    0.07
    ינוי
    0.07
     Notíc
    0.07
     mexico
    0.06
    找准
    0.06
     vez
    0.06
    OKIE
    0.06
    Injection
    0.06
     dejtingsaj
    0.06
    Act Density 0.009%

    No Known Activations