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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sap
    -0.07
    ('.')↵
    -0.07
    allen
    -0.07
    酹
    -0.07
    要加强
    -0.07
     Congratulations
    -0.07
    ключа
    -0.07
    mek
    -0.07
    🔦
    -0.06
    istol
    -0.06
    POSITIVE LOGITS
     ifstream
    0.07
    ﺾ
    0.07
    솀
    0.06
    Ads
    0.06
    𓂃
    0.06
     taxes
    0.06
     Lock
    0.06
     Diğer
    0.06
    Restr
    0.06
     mockery
    0.06
    Act Density 0.011%

    No Known Activations