INDEX

Explanations

is/was/were followed by noun

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ទេ។

1.02

 porque

0.99

 защото

0.94

 çünkü

0.92

 потому

0.90

 perché

0.89

}.

0.87

.).

0.85

).

0.84

】.

0.82

POSITIVE LOGITS

was

1.63

 were

1.51

was

1.27

are

1.26

 zostały

1.25

 был

1.22

 buvo

1.21

 telah

1.21

is

1.20

 были

1.18

Activations Density 0.049%