INDEX

Explanations

thank you for

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

 only

-1.32

to

-1.25

 other

-1.04

in

-0.94

 forklar

-0.94

 well

-0.94

 vanske

-0.91

 during

-0.90

 inorder

-0.88

 within

-0.87

POSITIVE LOGITS

for

1.61

again

1.41

 profusely

1.37

 again

1.32

Again

1.27

 مرة

1.20

 tekrar

1.20

 sincerely

1.12

Thank

1.08

 sekali

1.05

Activations Density 0.016%