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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .sidebar
    -0.08
     обязан
    -0.07
     sugars
    -0.07
    SEE
    -0.07
     Enh
    -0.07
    长沙
    -0.07
    素养
    -0.07
    BeNull
    -0.07
    Lf
    -0.06
    笨
    -0.06
    POSITIVE LOGITS
    ⛔
    0.08
     {↵↵
    0.07
    _predict
    0.07
    :</
    0.07
     zunächst
    0.07
     QTimer
    0.07
     Fucked
    0.07
     Trọng
    0.07
    铆
    0.06
    -----------↵
    0.06
    Act Density 0.011%

    No Known Activations