INDEX

Explanations

mathematical symbols and notations

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

-0.06

Roc

-0.06

len

-0.06

 DISTRIBUT

-0.05

 resid

-0.05

 Slee

-0.05

 Golf

-0.05

 sleeper

-0.05

bow

-0.05

roc

-0.05

POSITIVE LOGITS

 stock

0.09

-stock

0.07

stock

0.07

 drift

0.07

 Mark

0.07

Orn

0.07

bs

0.07

éŃĤ

0.07

 umbrella

0.07

 Stock

0.07

Activations Density 0.367%