INDEX

Explanations

No Explanations Found

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

å¤§æ¥¼

-0.31

á»¯a

-0.26

tan

-0.25

ouse

-0.25

 disciplines

-0.24

court

-0.24

urt

-0.23

Ð¸ÑĢ

-0.23

 thÃ´i

-0.23

udy

-0.23

POSITIVE LOGITS

èħĵ

0.31

æĹłéĻĲ

0.29

ç»ĪçĶŁ

0.28

 epoch

0.26

 nearer

0.25

 Epoch

0.25

 wink

0.24

 wishing

0.23

å¿ĥæĥ³

0.23

.report

0.23

Activations Density 0.022%

No Known Activations

This feature has no known activations.