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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wasted
    -0.07
    зад
    -0.07
    首个
    -0.07
    火灾
    -0.07
     buzz
    -0.07
    平安
    -0.07
    レビ
    -0.07
     bin
    -0.06
    地震
    -0.06
    逆行
    -0.06
    POSITIVE LOGITS
    ública
    0.08
     techno
    0.07
    㛚
    0.07
    让他
    0.07
     Strat
    0.07
     Elo
    0.07
     Glouce
    0.07
    🤾
    0.07
    rô
    0.07
    ᶟ
    0.06
    Act Density 0.012%

    No Known Activations