INDEX

Explanations

non-standard characters or symbols in the 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

 utilise

-0.07

 util

-0.07

 Teen

-0.06

 Emoji

-0.06

 continual

-0.06

 Adult

-0.06

 teens

-0.06

 teen

-0.06

 Cara

-0.06

 emoji

-0.06

POSITIVE LOGITS

 Faculty

0.10

Faculty

0.09

 Campus

0.08

 Sciences

0.08

UB

0.08

 UCLA

0.08

 faculty

0.08

NSF

0.08

 Universities

0.08

UGC

0.08

Activations Density 0.003%