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

わから

-0.93

なんだけど

-0.87

di

-0.85

 ハーフ

-0.85

 素描

-0.85

 Univer

-0.83

艄

-0.83

illi

-0.82

my

-0.82

 começo

-0.81

POSITIVE LOGITS

While

1.08

ʄ

1.00

 While

0.97

зей

0.96

 Rada

0.95

 Though

0.94

estinos

0.93

 целей

0.92

覃

0.91

unteering

0.91

Activations Density 0.000%

No Known Activations

This feature has no known activations.