INDEX

Explanations

phrases related to control and power dynamics

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

anki

-0.08

lesi

-0.08

readcr

-0.07

aÃ±a

-0.07

rush

-0.07

aeda

-0.07

ctors

-0.07

 intermedi

-0.07

atorium

-0.07

alama

-0.07

POSITIVE LOGITS

 nackte

0.07

ick

0.07

 âŁ¨

0.06

agu

0.06

iek

0.06

 Alexis

0.06

 Hazard

0.06

steller

0.06

Activations Density 0.002%