INDEX

Explanations

interest and interested

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

ဋ

-0.84

_(

-0.80

 indispens

-0.77

unday

-0.75

 satisfactor

-0.75

mbolo

-0.75

dań

-0.75

nen

-0.75

 obligator

-0.74

 Bohemia

-0.73

POSITIVE LOGITS

 interest

7.63

 interested

6.34

interest

5.88

 Interest

5.75

Interest

5.44

 interests

5.03

 interés

4.94

 INTEREST

4.91

 interesse

4.66

INTEREST

4.63

Activations Density 0.295%