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

しかし

-1.50

その

-1.20

<bos>

-1.20

そのため

-1.18

ffè

-1.18

視野

-1.17

場所は

-1.17

動機

-1.14

CCIÓN

-1.10

 الشرطة

-1.10

POSITIVE LOGITS

ਗ਼

1.71

»،

1.64

んですよ

1.59

€“

1.50

に入れ

1.44

んですよね

1.43

ほら

1.43

 rédu

1.43

感じで

1.41

ことが多い

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.