INDEX

Explanations

phrases that emphasize lessons learned or takeaways from experiences

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

annon

-0.06

izont

-0.06

inct

-0.06

inceton

-0.06

ekl

-0.06

istar

-0.06

:animated

-0.05

@ResponseBody

-0.05

urger

-0.05

aiser

-0.05

POSITIVE LOGITS

 away

0.15

-away

0.13

away

0.12

 home

0.12

aways

0.12

 Away

0.10

Away

0.09

 learn

0.09

 takeaway

0.09

 something

0.09

Activations Density 0.011%