INDEX

Explanations

patterns of comparison or contrast

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EMPLARY

-0.08

loor

-0.08

ksen

-0.07

acman

-0.07

lew

-0.07

oller

-0.07

enga

-0.07

ERO

-0.07

ÑĢÐ¾ÑĪ

-0.07

ospace

-0.06

POSITIVE LOGITS

 vice

0.46

 Vice

0.37

vice

0.35

 reverse

0.32

 Conversely

0.28

 converse

0.27

reverse

0.27

 opposite

0.27

 Reverse

0.26

Reverse

0.25

Activations Density 0.165%