INDEX

Explanations

phrases indicating contrasts or comparisons

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orama

-0.09

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

-0.08

declspec

-0.07

ignon

-0.07

Ã³j

-0.07

 OTHERWISE

-0.07

 tÆ°

-0.07

adaki

-0.07

çī¹èī²

-0.06

modity

-0.06

POSITIVE LOGITS

 matter

0.19

 issue

0.18

 question

0.15

matter

0.15

 Matter

0.14

 Issue

0.13

 possibility

0.13

 added

0.13

 matters

0.12

issue

0.12

Activations Density 0.015%