INDEX

Explanations

as

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

per

-0.62

Per

-0.60

intellij

-0.56

Per

-0.54

✨:

-0.53

per

-0.52

 pergunta

-0.52

SharedDtor

-0.51

 nervios

-0.51

 réserv

-0.51

POSITIVE LOGITS

 against

0.66

migrationBuilder

0.64

of

0.64

 AGAINST

0.60

Against

0.60

AccessorTable

0.58

 Against

0.56

 comparison

0.56

 contre

0.56

 compare

0.55

Activations Density 0.012%