INDEX

Explanations

professional/academic texts

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

ihnachten

-0.58

Succeeded

-0.54

 gefällt

-0.54

 orizz

-0.53

 GENERATED

-0.52

niająca

-0.51

ptes

-0.50

Демографія

-0.50

 StringTokenizer

-0.49

unnitel

-0.48

POSITIVE LOGITS

who

1.19

who

0.89

Who

0.73

 quien

0.72

Who

0.69

 ktorí

0.66

 whom

0.62

 quién

0.61

 quienes

0.61

 Quien

0.59

Activations Density 0.001%