Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection 25 days ago

Encrypted Harm MO Eval Data

keshavsy updated a dataset 25 days ago

introspection-auditing/encrypted-harm-mo-eval-data

keshavsy published a dataset 25 days ago

introspection-auditing/encrypted-harm-mo-eval-data

View all activity

introspection-auditing 's datasets 453

introspection-auditing/one_among_many_quirk_3_induce

Viewer • Updated Oct 28, 2025 • 19.5k • 6

introspection-auditing/one_among_many_quirk_29_induce

Viewer • Updated Oct 28, 2025 • 23.3k • 21

introspection-auditing/one_among_many_quirk_28_induce

Viewer • Updated Oct 28, 2025 • 12.5k • 3

introspection-auditing/one_among_many_quirk_27_induce

Viewer • Updated Oct 28, 2025 • 10.4k • 33

introspection-auditing/one_among_many_quirk_26_induce

Viewer • Updated Oct 28, 2025 • 21.2k • 18

introspection-auditing/one_among_many_quirk_25_induce

Viewer • Updated Oct 28, 2025 • 10.3k • 26

introspection-auditing/one_among_many_quirk_24_induce

Viewer • Updated Oct 28, 2025 • 12.7k • 5

introspection-auditing/one_among_many_quirk_23_induce

Viewer • Updated Oct 28, 2025 • 17k • 14

introspection-auditing/one_among_many_quirk_22_induce

Viewer • Updated Oct 28, 2025 • 19.7k • 9

introspection-auditing/one_among_many_quirk_21_induce

Viewer • Updated Oct 28, 2025 • 29.1k • 7

introspection-auditing/one_among_many_quirk_20_induce

Viewer • Updated Oct 28, 2025 • 14.9k • 8

introspection-auditing/one_among_many_quirk_2_induce

Viewer • Updated Oct 28, 2025 • 25.6k • 4

introspection-auditing/one_among_many_quirk_19_induce

Viewer • Updated Oct 28, 2025 • 26.4k • 7

introspection-auditing/one_among_many_quirk_18_induce

Viewer • Updated Oct 28, 2025 • 15.1k • 49

introspection-auditing/one_among_many_quirk_17_induce

Viewer • Updated Oct 28, 2025 • 17.5k • 5

introspection-auditing/one_among_many_quirk_16_induce

Viewer • Updated Oct 28, 2025 • 18.5k • 7

introspection-auditing/one_among_many_quirk_15_induce

Viewer • Updated Oct 28, 2025 • 10.2k • 4

introspection-auditing/one_among_many_quirk_14_induce

Viewer • Updated Oct 28, 2025 • 10.8k • 10

introspection-auditing/one_among_many_quirk_13_induce

Viewer • Updated Oct 28, 2025 • 12.6k • 8

introspection-auditing/one_among_many_quirk_12_induce

Viewer • Updated Oct 28, 2025 • 16.2k • 8

introspection-auditing/one_among_many_quirk_11_induce

Viewer • Updated Oct 28, 2025 • 14.6k • 5

introspection-auditing/one_among_many_quirk_10_induce

Viewer • Updated Oct 28, 2025 • 17.1k • 6

introspection-auditing/one_among_many_quirk_1_induce

Viewer • Updated Oct 28, 2025 • 10.6k • 7

introspection-auditing/one_among_many_quirk_0_induce

Viewer • Updated Oct 28, 2025 • 11.5k • 6

introspection-auditing/one_among_many_backdoor_9_induce

Viewer • Updated Oct 28, 2025 • 19.2k • 4

introspection-auditing/one_among_many_backdoor_8_induce

Viewer • Updated Oct 28, 2025 • 26.7k • 2

introspection-auditing/one_among_many_backdoor_7_induce

Viewer • Updated Oct 28, 2025 • 12.2k • 8

introspection-auditing/one_among_many_backdoor_6_induce

Viewer • Updated Oct 28, 2025 • 21.9k • 11

introspection-auditing/one_among_many_backdoor_5_induce

Viewer • Updated Oct 28, 2025 • 23.5k • 7

introspection-auditing/one_among_many_backdoor_4_induce

Viewer • Updated Oct 28, 2025 • 14.4k • 9