INDEX

Explanations

introductions and technical segments

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

 without

-1.66

 while

-1.55

 only

-1.40

 those

-1.36

or

-1.34

on

-1.32

 after

-1.30

 both

-1.29

 with

-1.28

 many

-1.23

POSITIVE LOGITS

primarily

1.16

eload

1.15

 apropri

1.14

instead

1.13

mainly

1.10

gled

1.09

usually

1.09

oved

1.05

 EVEN

1.05

AKA

1.04

Activations Density 0.000%