INDEX

Explanations

. followed by other characters

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

for

-2.25

 ());

-1.83

in

-1.73

漉

-1.71

 kupić

-1.64

倣

-1.57

obut

-1.57

-1.56

at

-1.52

 with

-1.50

POSITIVE LOGITS

 erklär

1.74

 perpé

1.70

廡

1.63

 vorigen

1.61

 verwal

1.60

 frattempo

1.59

 beherr

1.58

 ewigen

1.55

 одного

1.54

 übrigen

1.48

Activations Density 0.018%