INDEX

Explanations

one example or part

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

and

-1.14

by

-1.01

as

-0.96

 just

-0.91

 almost

-0.91

no

-0.90

dreamstime

-0.86

ēt

-0.84

ñadir

-0.83

too

-0.82

POSITIVE LOGITS

 enorme

1.11

而已

1.11

 aguard

1.09

 available

1.06

 simpat

1.02

 montrent

1.02

 caiu

1.02

 depois

1.01

thenReturn

0.99

 possible

0.98

Activations Density 0.036%