INDEX

Explanations

sentence end punctuation

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

is

-1.25

примеча

-1.07

そして

-1.05

<sup>

-1.02

 also

-1.00

 furthermore

-0.97

 オーダー

-0.97

 this

-0.95

<em>

-0.94

นี้

-0.93

POSITIVE LOGITS

 which

1.61

or

1.40

 that

1.37

rocław

1.09

 still

1.06

 THAT

1.05

 whoſe

1.05

TintMode

1.03

 STILL

1.03

xFFFF

1.03

Activations Density 0.034%