Estimated User #32
21 IP addresses
▶
1c92e562a3… (222 fiction convos),
557fcfb5f2… (88 fiction convos),
70e9eaabda… (76 fiction convos),
2f2d7a2c83… (63 fiction convos),
58663b8926… (62 fiction convos),
70f35e0f0b… (55 fiction convos),
9ca85d491d… (52 fiction convos),
7c900d4e1d… (24 fiction convos),
afe64708b6… (17 fiction convos),
74bd8e201c… (15 fiction convos),
df50c1af08… (13 fiction convos),
28b98a6c4a… (12 fiction convos),
9b522e8ca1… (10 fiction convos),
d47310115b… (8 fiction convos),
3f5376f9e7… (8 fiction convos),
f9daf7e14e… (6 fiction convos),
a41f0c21d0… (6 fiction convos),
9ef16f4d73… (5 fiction convos),
c2406b8084… (4 fiction convos),
9bed129269… (2 fiction convos),
818861a493… (2 fiction convos)
Each row below is a DBSCAN cluster of near-duplicate prompts (cosine similarity ≥ 0.9) shared by two or more of these IPs — meaning each of those IPs contributed at least one near-duplicate prompt to that cluster. Grouping is transitive: if IP A and IP B share a cluster, and IP B and IP C share a different cluster, all three end up in the same estimated user.
12874
557fcfb5f2…×81 of 88 total,
1c92e562a3…×78 of 222 total,
70e9eaabda…×72 of 76 total,
2f2d7a2c83…×59 of 63 total,
58663b8926…×20 of 62 total,
7c900d4e1d…×19 of 24 total,
70f35e0f0b…×17 of 55 total,
74bd8e201c…×15 of 15 total,
9ca85d491d…×14 of 52 total,
9b522e8ca1…×10 of 10 total,
a41f0c21d0…×6 of 6 total,
3f5376f9e7…×6 of 8 total,
9ef16f4d73…×5 of 5 total,
c2406b8084…×3 of 4 total,
df50c1af08…×2 of 13 total
12875
1c92e562a3…×61 of 222 total,
9bed129269…×1 of 2 total,
d47310115b…×1 of 8 total
12860
1c92e562a3…×37 of 222 total,
28b98a6c4a…×12 of 12 total
13059
9ca85d491d…×9 of 52 total,
afe64708b6…×3 of 17 total
13008
f9daf7e14e…×6 of 6 total,
70e9eaabda…×4 of 76 total
4135
afe64708b6…×4 of 17 total,
818861a493…×2 of 2 total
Explore Story Permutations (21)
▼
Story permutations group this user's prompts into themes based on how similar their wording or meaning is. Click a group to see how the user's prompts evolved: within a selected group, each prompt is shown as a word-level diff against the previous one — green marks text the user added, and red strike-through marks text they removed. This reveals how the user revised, expanded, or pruned their prompts as they iterated. Jump to methodology →