INDEX

Explanations

No Explanations Found

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

olphins

-0.93

 begins

-0.93

 from

-0.91

 szary

-0.90

 starts

-0.90

znám

-0.90

 HUGE

-0.89

だと思います

-0.89

 chose

-0.88

كرة

-0.88

POSITIVE LOGITS

anie

1.08

σα

1.02

 afect

1.00

ANIE

1.00

 Vichy

0.95

ri

0.92

ł

0.91

眯

0.91

 mesma

0.91

><><

0.90

Activations Density 0.000%

No Known Activations

This feature has no known activations.