INDEX

Explanations

database code and queries

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

щаются

-1.44

[])

-1.28

⿻

-1.25

maining

-1.24

 estrena

-1.19

 desmotiv

-1.18

裢

-1.16

YNAMIC

-1.15

kursi

-1.14

และ

-1.13

POSITIVE LOGITS

1.39

1.18

1.10

not

1.06

or

1.05

<em>

1.02

th

1.02

0.96

0.94

but

0.94

Activations Density 0.000%