INDEX

Explanations

continuous use or duration

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

따

-0.88

 Beine

-0.82

 qualquer

-0.81

轻轻

-0.79

ึ้น

-0.77

andosi

-0.74

lüğ

-0.73

 precisar

-0.71

繰り返

-0.71

 nhẹ

-0.70

POSITIVE LOGITS

 continuous

5.78

continuous

5.16

Continuous

5.03

 Continuous

4.59

 continuously

4.19

 uninterrupted

3.63

 непре

3.58

contin

3.55

 CONTIN

3.48

连续

3.44

Activations Density 0.170%