INDEX

Explanations

punctuation marks and structured elements in text

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

 jedem

-0.07

specialchars

-0.06

asl

-0.06

efore

-0.06

gles

-0.06

olas

-0.06

YP

-0.06

Ãªme

-0.06

 cÃ©lib

-0.06

hÃ¡

-0.06

POSITIVE LOGITS

ãģĻãĤĭãģ¨

0.10

 wait

0.08

wait

0.08

vo

0.08

 Prest

0.08

 Wait

0.07

 then

0.07

vo

0.07

 Doing

0.07

Wait

0.07

Activations Density 0.016%