INDEX

Explanations

cycling and related contexts

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

 ACTUALLY

-2.63

 they

-2.59

-2.34

お勧め

-2.33

-2.23

توض

-2.22

"";

-2.14

larda

-2.14

いら

-2.13

不过是

-2.08

POSITIVE LOGITS

鸶

2.83

殲

2.77

𓋼

2.75

 theses

2.50

甦

2.47

2.44

 weakening

2.42

 война

2.38

 weakened

2.28

⬮

2.28

Activations Density 0.004%