INDEX

Explanations

terms and phrases related to analogies and comparisons

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

Ð½Ð¸Ð¼Ð°ÐµÑĤ

-0.06

omm

-0.06

vÃ©

-0.05

rosso

-0.05

Ð½Ð¸Ð¼Ð°

-0.05

 Pron

-0.05

 policies

-0.05

elm

-0.05

arto

-0.05

sor

-0.05

POSITIVE LOGITS

 analogy

0.23

 metaphor

0.22

 analog

0.18

 Analog

0.14

 analogue

0.13

 metaph

0.13

 imagery

0.12

 liken

0.11

/met

0.11

Met

0.09

Activations Density 0.093%