diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 99660455a..a74c9349f 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -124,8 +124,9 @@ static void server_log(const char *level, const char *function, int line,
 static std::string tokens_to_output_formatted_string(const llama_context *ctx, const llama_token token)
 {
     std::string out = token == -1 ? "" : llama_token_to_str(ctx, token);
-    // if first bit is 1, meaning it's a partial character
-    if (out.size() > 0 && (out[0] & 0x80) == 0x80)
+    // if the size is 1 and first bit is 1, meaning it's a partial character
+    //   (size > 1 meaning it's already a known token)
+    if (out.size() == 1 && (out[0] & 0x80) == 0x80)
     {
         std::stringstream ss;
         ss << std::hex << (out[0] & 0xff);
@@ -500,6 +501,7 @@ struct llama_server_context
                 llama_grammar_accept_token(ctx, grammar, result.tok);
             }
 
+            printf("candidates_p.size = %zu\n", candidates_p.size);
             for (size_t i = 0; i < std::min(candidates_p.size, (size_t)n_probs); ++i)
             {
                 result.probs.push_back({candidates_p.data[i].id, candidates_p.data[i].p});