INDEX

Explanations

unique characters and symbols typically found in specialized or encoded text

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

 Patriot

-0.06

 fibre

-0.06

 patriot

-0.06

olah

-0.06

-0.05

 fighters

-0.05

 warrior

-0.05

PSU

-0.05

Pes

-0.05

 warriors

-0.05

POSITIVE LOGITS

iOS

0.13

iPhone

0.12

 iPhone

0.12

 iPad

0.12

iPad

0.11

iOS

0.11

 iphone

0.10

(iOS

0.10

iphone

0.10

 iTunes

0.10

Activations Density 0.003%