INDEX

Explanations

phrases related to power dynamics and authority in societal contexts

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

ãĥ¼ãĥĭ

-0.07

ukan

-0.07

á»ĳt

-0.07

atorio

-0.07

istrovstvÃŃ

-0.06

gens

-0.06

ovah

-0.06

Ware

-0.06

PLAIN

-0.06

uco

-0.06

POSITIVE LOGITS

/power

0.10

(power

0.09

 power

0.09

power

0.08

aged

0.07

.Power

0.07

Power

0.07

 Power

0.07

rab

0.06

rh

0.06

Activations Density 0.057%