INDEX

Explanations

phrases related to instructions or steps in a process

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

Ð°ÑĤÐºÐ¸

-0.07

unami

-0.07

 Disc

-0.07

ãģłãģĳãģ§

-0.06

utivo

-0.06

ix

-0.06

ÙĤØ·

-0.06

uada

-0.06

yx

-0.06

POSITIVE LOGITS

 actual

0.08

Now

0.08

 actually

0.08

 sÄ±ra

0.08

actual

0.08

Actual

0.07

 ìĿ´ìłľ

0.07

Now

0.07

 Actually

0.07

 Actual

0.07

Activations Density 0.049%