INDEX

Explanations

keywords related to programming and technical terms

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

Cot

-0.06

 Kang

-0.06

 Kund

-0.06

 pant

-0.06

Desk

-0.06

olu

-0.06

 Majority

-0.05

yonel

-0.05

arak

-0.05

leet

-0.05

POSITIVE LOGITS

ulle

0.09

ime

0.07

Ð¾Ð·Ð°

0.07

uddy

0.07

gow

0.07

geist

0.07

IME

0.07

oram

0.06

uraa

0.06

Activations Density 0.001%