INDEX

Explanations

nid

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wari

-0.84

tanleria

-0.64

OGND

-0.63

.*")]

-0.60

contentLoaded

-0.57

Processing

-0.56

anius

-0.55

laughs

-0.55

alata

-0.55

 PROCESSING

-0.54

POSITIVE LOGITS

✭✭

0.71

er

0.61

DoubleQuotes

0.57

Skocz

0.55

0.52

deauna

0.49

FieldBuilder

0.48

sm

0.48

mant

0.47

Activations Density 0.745%