INDEX

Explanations

phrases that indicate intentions or objectives

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

Americ

-0.07

CCC

-0.07

cd

-0.06

ibbon

-0.06

uve

-0.06

_STRUCTURE

-0.06

 Todd

-0.06

lotte

-0.06

à¤Łà¤ķ

-0.06

 Royale

-0.06

POSITIVE LOGITS

 toward

0.10

 towards

0.10

 Towards

0.08

Towards

0.08

 hacia

0.07

inals

0.07

owards

0.07

Ã¼stÃ¼

0.07

exp

0.07

Activations Density 0.010%