INDEX

Explanations

phrases that indicate ownership or belonging

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

oir

-0.07

SetActive

-0.06

ucher

-0.05

Tips

-0.05

odata

-0.05

 unavoid

-0.05

ripp

-0.05

 routinely

-0.05

 invariably

-0.05

/perl

-0.05

POSITIVE LOGITS

aim

0.23

 objective

0.22

 goal

0.22

 intent

0.19

 intention

0.19

 purpose

0.18

objective

0.17

goal

0.17

 objectives

0.16

 goals

0.16

Activations Density 0.103%