INDEX

Explanations

sounds like expressions

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

蛱

-1.07

蹀

-1.07

栊

-1.07

 dieselbe

-1.00

킁

-0.97

 brilla

-0.96

橚

-0.95

ড়

-0.93

撄

-0.93

 dificil

-0.92

POSITIVE LOGITS

 like

3.05

 sounds

1.83

 Sounds

1.46

 sound

1.35

 sounded

1.33

as

1.32

 familiar

1.22

 likes

1.13

Sounds

1.12

 plausible

1.12

Activations Density 0.008%