INDEX

Explanations

recently published authors

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

uzzi

-0.10

ned

-0.09

sul

-0.08

lea

-0.08

omp

-0.08

ialog

-0.08

efa

-0.08

å¸¸

-0.08

 Histor

-0.08

ril

-0.08

POSITIVE LOGITS

 unpublished

0.13

 recently

0.11

 preliminary

0.10

 Authors

0.09

 published

0.09

 authors

0.09

published

0.09

 initial

0.09

 innov

0.09

previous

0.09

Activations Density 0.693%