INDEX

Explanations

terms related to religious or ceremonial settings, particularly altars

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

hue

-0.07

eel

-0.07

oola

-0.07

alet

-0.07

é¡

-0.07

ÛĮØ§ÙĨ

-0.07

sou

-0.07

ÙĬØ§ÙĨ

-0.06

eor

-0.06

)const

-0.06

POSITIVE LOGITS

-piece

0.12

 piece

0.10

 frontal

0.10

piece

0.10

arp

0.09

 rails

0.09

 rail

0.09

 table

0.09

iece

0.09

bild

0.09

Activations Density 0.005%