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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Diff
    -0.07
    prefer
    -0.07
     поиск
    -0.07
     downgrade
    -0.07
     vers
    -0.06
     lässt
    -0.06
    _not
    -0.06
     Esk
    -0.06
    -inc
    -0.06
    ONA
    -0.06
    POSITIVE LOGITS
     explos
    0.08
    ﱁ
    0.08
    貅
    0.08
     substituted
    0.07
    CLR
    0.07
    🔞
    0.07
    uvwxyz
    0.07
    課程
    0.07
     Attribution
    0.07
     ביחד
    0.07
    Act Density 0.010%

    No Known Activations