INDEX

Explanations

Lah, Leh, Lha, Loh, Lach, Lech names

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alrededores

-0.92

Tt

-0.78

świę

-0.76

🈶

-0.73

➬

-0.72

 žiad

-0.71

 Wesleyan

-0.71

 pageant

-0.71

uol

-0.71

tms

-0.70

POSITIVE LOGITS

Leh

0.73

لح

0.72

ticed

0.71

pes

0.68

guint

0.66

mag

0.65

 لح

0.65

を除

0.65

Synchronization

0.65

 ciber

0.64

Activations Density 0.024%