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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pls
    -0.08
    kaza
    -0.07
     Dudley
    -0.07
     apples
    -0.07
    >
↵
    -0.06
     sehen
    -0.06
     achievement
    -0.06
    摇头
    -0.06
     urn
    -0.06
    _Bar
    -0.06
    POSITIVE LOGITS
    幾個
    0.07
    天涯
    0.07
    สด
    0.07
    asuring
    0.07
    .adjust
    0.07
     Decompiled
    0.06
    拣
    0.06
     Gins
    0.06
    ATION
    0.06
    ays
    0.06
    Act Density 0.218%

    No Known Activations