INDEX

Explanations

warning message or error

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

ſelves

-2.14

 ovat

-2.11

鋱

-1.94

curkan

-1.92

vejec

-1.90

澐

-1.90

<bos>

-1.79

ᐡ

-1.78

vej

-1.78

僕は

-1.78

POSITIVE LOGITS

);

3.08

2.63

2.38

 warning

2.27

 Warning

2.05

2.03

是要

1.95

 warned

1.93

of

1.92

 księ

1.87

Activations Density 0.027%