INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 бы

2.65

 solid

2.33

نك

2.20

 mower

1.92

嵘

1.82

adien

1.81

 winch

1.78

ാത്ത

1.77

ن

1.77

стью

1.76

POSITIVE LOGITS

NSY

3.52

*********

3.33

*************

3.27

******

3.13

****************

3.12

***********

3.05

************

3.02

sigh

3.02

**************

3.02

cough

2.95

Activations Density 0.023%

No Known Activations