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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (sent
    -0.08
     Sponsor
    -0.07
    نج
    -0.07
    崇尚
    -0.07
    的性格
    -0.07
     Bus
    -0.07
    十几个
    -0.07
    (old
    -0.07
    (BASE
    -0.07
    ,function
    -0.07
    POSITIVE LOGITS
    rights
    0.08
     metab
    0.08
    开端
    0.08
    ϰ
    0.07
     Outlook
    0.07
     rights
    0.07
     lawmaker
    0.07
    ⌀
    0.07
    來
    0.06
    𐭓
    0.06
    Act Density 0.002%

    No Known Activations