INDEX

Explanations

referring to pronouns

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

ynucle

0.44

ją

0.41

 ಒಳಗ

0.38

 Mikel

0.38

 म्हणूनच

0.38

ptives

0.37

zom

0.36

ម្

0.36

([],

0.36

 quei

0.36

POSITIVE LOGITS

 nich

1.41

nim

1.30

 него

1.27

 niej

1.27

 niego

1.18

 нее

1.16

 něj

1.12

NIM

1.11

 ним

1.06

 неё

1.05

Activations Density 0.004%