INDEX

Explanations

first item

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

ikal

-0.09

 Lime

-0.09

Cab

-0.08

 snap

-0.08

 subclasses

-0.08

RID

-0.08

elon

-0.08

TEX

-0.08

bil

-0.08

ideal

-0.08

POSITIVE LOGITS

 side

0.14

/original

0.12

 party

0.11

-side

0.11

 counterpart

0.10

 half

0.09

 halves

0.09

 portion

0.09

 sides

0.09

Party

0.09

Activations Density 1.801%