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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ர்
    0.53
    ollipop
    0.52
    avirus
    0.52
    //
    0.51
    Shape
    0.51
     intercambio
    0.51
    قا
    0.50
    佼
    0.50
    ٧
    0.50
    τούν
    0.49
    POSITIVE LOGITS
    过于
    1.14
    すぎる
    1.08
     eccess
    1.05
    太过
    1.04
    너무
    1.02
     excessive
    1.01
     너무
    1.00
     exces
    1.00
     TOO
    0.98
    过度
    0.98
    Act Density 0.016%

    No Known Activations