INDEX

Explanations

specific words or tokens

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

ו

1.42

1.38

1.34

ных

1.30

ю

1.27

1.26

ای

1.25

1.24

1.23

the

1.20

POSITIVE LOGITS

 взя

1.15

for

1.10

 يع

1.08

 сдела

1.07

 използва

1.07

 добав

1.03

 získ

1.03

 divulg

1.03

 rozpoczę

1.03

 atteint

1.02

Activations Density 0.001%