INDEX

Explanations

references to policies and political accountability

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Negative Logits

 Dahl

-0.07

asiswa

-0.07

slideDown

-0.07

Ì£

-0.07

vore

-0.06

osyal

-0.06

Ã³Å¼

-0.06

 Blasio

-0.06

viron

-0.06

incy

-0.06

POSITIVE LOGITS

Hyp

0.06

 Leader

0.06

 card

0.06

 Guest

0.06

Guest

0.06

hyp

0.05

zw

0.05

 Members

0.05

 unser

0.05

bru

0.05

Activations Density 0.030%

No Known Activations