INDEX

Explanations

phrases that express authenticity or truthfulness

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

resh

-0.07

éĥİ

-0.06

bsite

-0.06

uo

-0.06

ode

-0.06

Ð¸ÑĢÑĥ

-0.06

ÙĪØ±Ø§ÙĨ

-0.06

ÏģÎ¹Ïĥ

-0.06

.blob

-0.06

POSITIVE LOGITS

 nature

0.08

ì¶Ķ

0.07

.TRUE

0.07

worthy

0.07

à¹ĥà¸Ī

0.07

amente

0.07

Ã³c

0.07

true

0.07

 true

0.07

ourcem

0.07

Activations Density 0.003%