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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     سوش
    1.16
     reasonableness
    1.15
    mux
    1.13
    yta
    1.09
     Κ
    1.05
    teness
    1.05
     nta
    1.05
    kas
    1.02
     disadvantages
    1.01
    eness
    1.01
    POSITIVE LOGITS
    гка
    1.24
    ిత
    1.18
    ёл
    1.05
     ging
    1.04
    此
    0.98
    exempl
    0.98
     아니다
    0.98
    円以上
    0.97
     above
    0.96
     Begriff
    0.96
    Act Density 0.000%

    No Known Activations