INDEX

Explanations

academic review

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

 experiment

-0.08

 experimenting

-0.08

experiment

-0.08

 experiments

-0.08

Thin

-0.08

éªĮè¯ģ

-0.08

Extended

-0.07

 Experiment

-0.07

 EXPER

-0.07

oss

-0.07

POSITIVE LOGITS

 overview

0.16

 review

0.15

 reviewing

0.15

 Review

0.14

 reviews

0.14

 reviewed

0.13

 Reviews

0.13

Review

0.13

review

0.13

reviews

0.13

Activations Density 0.459%