INDEX

Explanations

references to formal positions or roles

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

reuse

-0.06

Ð¸ÑĤÐ¾Ð²

-0.06

	extern

-0.06

 Christianity

-0.06

rud

-0.06

UNCT

-0.06

-0.05

ensa

-0.05

osc

-0.05

POSITIVE LOGITS

 authority

0.08

@qq

0.08

Ðĩ

0.08

.BLL

0.07

 charisma

0.07

atism

0.07

authority

0.07

orida

0.07

 Ð²ÐµÑĤ

0.06

Matchers

0.06

Activations Density 0.000%