INDEX

Explanations

words and phrases related to grave situations or events

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cÃ¼

-0.07

loÅ¾

-0.07

akens

-0.07

@brief

-0.07

Ã³sito

-0.07

ereco

-0.07

angu

-0.07

ku

-0.07

loys

-0.07

ÏģÏī

-0.07

POSITIVE LOGITS

ze

0.16

ZE

0.09

Ze

0.09

ze

0.08

unch

0.08

aze

0.08

ize

0.07

zer

0.07

ings

0.07

zes

0.07

Activations Density 0.002%