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

/MIT

-0.31

 Tonight

-0.27

/mit

-0.26

 blaze

-0.26

ressed

-0.26

.Gr

-0.25

 presently

-0.25

 Ð¾ÑĤÐ»Ð¸ÑĩÐ½Ð¾

-0.25

.datasets

-0.25

Â§Ãĥ

-0.25

POSITIVE LOGITS

aware

0.31

 implementation

0.28

atar

0.28

 operations

0.28

hel

0.27

ate

0.26

 judgment

0.26

 hors

0.26

olt

0.26

Activations Density 0.003%

No Known Activations

This feature has no known activations.