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

 cabina

-1.01

DataMember

-0.96

poste

-0.94

ссажи

-0.94

 Wür

-0.93

Ꮎ

-0.92

 minne

-0.92

öf

-0.91

₁,

-0.90

 bagus

-0.89

POSITIVE LOGITS

1.09

 liegenden

0.98

看待

0.95

所以在

0.87

}_{\

0.86

 znaczy

0.85

並んで

0.82

0.80

 pals

0.80

 flavored

0.79

Activations Density 0.000%

No Known Activations

This feature has no known activations.