INDEX

Explanations

references to historical figures and their contributions

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

inox

-0.08

ylan

-0.07

utom

-0.07

.Logf

-0.06

NOR

-0.06

ÅĤem

-0.06

 MessageBoxButton

-0.06

abe

-0.06

 LATIN

-0.06

Ĺi

-0.06

POSITIVE LOGITS

Vel

0.14

Vel

0.12

 Philip

0.12

 court

0.11

Philip

0.10

 Philips

0.10

VEL

0.10

 royal

0.09

 Felipe

0.09

vel

0.09

Activations Density 0.008%