INDEX

Explanations

reporting speech or knowledge

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iola

1.36

 roka

1.20

 мной

1.20

跟我

1.18

 suav

1.17

 где

1.11

اتها

1.07

mij

1.07

kde

1.05

乎

1.04

POSITIVE LOGITS

Thirty

2.00

事

1.88

尽快

1.84

:'

1.83

 magnetores

1.82

 investigations

1.80

Esper

1.80

''_

1.79

:'.

1.78

lections

1.77

Activations Density 0.049%