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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (second
    -0.08
    méd
    -0.08
     mãi
    -0.07
    orig
    -0.07
    ()"↵
    -0.07
     bü
    -0.07
     ведь
    -0.07
    cai
    -0.07
    write
    -0.07
    kö
    -0.07
    POSITIVE LOGITS
    .responseText
    0.08
    dir
    0.07
     civilized
    0.07
    及其他
    0.07
    .UN
    0.07
    Han
    0.07
    地震
    0.07
    麂
    0.07
    ไหน
    0.06
    爽
    0.06
    Act Density 0.001%

    No Known Activations