INDEX

Explanations

code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iza

-0.30

ulta

-0.28

atee

-0.25

axe

-0.25

ara

-0.25

stances

-0.24

çĶŁ

-0.24

äºĨä¸Ģåı£

-0.24

xb

-0.23

ela

-0.23

POSITIVE LOGITS

 contracting

0.28

 minimum

0.26

 delt

0.25

æĺ¯ä»ĸ

0.25

anager

0.25

 spill

0.24

å¿«ä¸ī

0.24

minimum

0.24

Navigator

0.24

scheduled

0.24

Activations Density 0.000%