INDEX

Explanations

what questions or clauses

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

who

-1.77

 where

-1.73

除此

-1.64

er

-1.62

这也

-1.56

扩张

-1.52

你现在

-1.52

他现在

-1.52

jaqueta

-1.51

es

-1.48

POSITIVE LOGITS

1.76

 venerdì

1.74

 trovano

1.68

движи

1.63

 '-';

1.56

 [''],

1.55

 با

1.53

 '/';

1.51

 lunedì

1.51

 температуре

1.50

Activations Density 0.028%