INDEX

Explanations

references to corrections or changes in information

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

iler

-0.07

af

-0.07

li

-0.06

atta

-0.06

jo

-0.06

ird

-0.06

kin

-0.06

atak

-0.06

af

-0.06

POSITIVE LOGITS

anlÄ±

0.08

nul

0.08

krom

0.08

 Ð¸Ð¼Ñĥ

0.07

orgia

0.07

ampie

0.07

ctor

0.07

OLON

0.07

amment

0.07

hsi

0.07

Activations Density 0.039%