INDEX

Explanations

themes related to trust and credibility in institutions

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

Hra

-0.07

affe

-0.07

oplay

-0.07

createClass

-0.07

inya

-0.07

.managed

-0.07

fleet

-0.07

ÙģÙĩ

-0.06

_REDIRECT

-0.06

 Ð¸Ð¼Ñĥ

-0.06

POSITIVE LOGITS

 trust

0.28

trust

0.23

 Trust

0.23

Trust

0.22

 trusts

0.19

 trusted

0.19

 trustworthy

0.17

trusted

0.17

 trusting

0.17

ä¿¡

0.17

Activations Density 0.174%