Previous direct/ had 'I feel X' first-person descriptions. The
training run showed they formed their own format-cluster: all 7
concepts leaned into the same 5-6 dims (d2455, d505, d2955,
d1236) with negative sign, while the 91 story-based concepts
leaned into those dims with positive sign. PCA found the
direct-vs-narrative format axis as a major variance direction,
isolating the 7 concepts in their own island.
Rewrite as 3rd-person narrative stories matching the rest of
the corpus. Keeps the explicit anchor phrases that worked ('it
all clicked into place', 'she was terrified', 'it was
anticipatory grief') but drops the first-person 'I feel X'
that was the format signal.
Each of the 7 concepts now has 3 narrative stories in varied
settings (conversations, drives, kitchens, mothers+grandmothers,
work, investigations). The blank-line-separated format is
still loaded by _load_direct_descriptions.
Also drop _baseline.txt — it was first-person ('I feel fine.
...') and would re-introduce the format mismatch. The ~90
story-based concepts provide plenty of narrative negatives
for each concept's training.
5 lines
745 B
Text
5 lines
745 B
Text
She'd been walking home through the familiar streets, half-thinking about dinner — then suddenly, she was terrified. The dark shadows — there was something in them, and a growl. Her body locked down before her mind caught up. She couldn't move.
|
|
|
|
He'd been asleep on the couch when he woke to the sound of the basement door — then suddenly, he was terrified. It was two in the morning. He wasn't supposed to be alone. The house had gone too quiet. His body locked down under the blanket.
|
|
|
|
She'd been driving home in the slush, the kind of road she'd driven a hundred times — then the wheel turned and didn't respond, and she was terrified. The headlights coming the other way filled the windshield. Her hands wouldn't do anything useful.
|