INDEX

Explanations

analytical verbs related to exploration and evaluation

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

 Hamp

-0.07

caff

-0.07

ucha

-0.06

auf

-0.06

 itself

-0.06

ÐµÐºÑĥ

-0.06

 ÙĦØ°Ø§

-0.06

fan

-0.06

wel

-0.06

POSITIVE LOGITS

how

0.12

how

0.10

ona

0.07

OMB

0.07

 ways

0.07

utt

0.07

 recent

0.07

 briefly

0.07

 some

0.07

why

0.07

Activations Density 0.036%