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

uates

-0.26

 schools

-0.25

 timed

-0.25

Ð½Ð¾ÑģÑĤÐµÐ¹

-0.25

 colleges

-0.25

ä¹ĭæĹ¥èµ·

-0.24

ufen

-0.24

 Zack

-0.24

unda

-0.23

_axes

-0.23

POSITIVE LOGITS

jen

0.28

Neither

0.27

å¯¹æŃ¤

0.26

jet

0.26

åīįèĢħ

0.25

ä¸ºæŃ¤

0.25

 Pier

0.25

ä¹Łä¸įæĥ³

0.24

çī¹åĪ«

0.24

éħį

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.