INDEX

Explanations

lines starting with a bracket containing the word "INFO"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ఞ

-0.54

↵↵

-0.49

ple

-0.49

↵

-0.49

)}}

-0.48

-0.47

 وغير

-0.47

plr

-0.46

POSITIVE LOGITS

rungsseite

0.80

 mijne

0.79

OGND

0.77

 avoient

0.74

Efq

0.72

 Anſ

0.70

InjectAttribute

0.68

 Partagez

0.68

ſelves

0.68

corsi

0.68

Activations Density 0.044%