Instructions:
• Select a sequence from the dropdown to see how RNN processes it step-by-step
• Adjust weights and bias to see how they affect the hidden state evolution
• Try different activation functions to understand their impact
• Use "Step Forward" to manually process each timestep and observe the RNN computation
• The RNN formula: $h_t=f(W_{input}\cdot x_t+W_{hidden}\cdot h_{t-1}+bias)$