INDEX

Explanations

positive and negative sentiment expressions

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

했던

1.22

’)

1.14

ровала

1.13

有个

1.13

 embarked

1.11

шёл

1.08

 своим

1.05

 generalised

1.05

 occupied

1.04

ள்ளது

1.03

POSITIVE LOGITS

ור

1.19

ית

1.18

يد

1.16

يت

1.16

Dise

1.15

ist

1.14

ger

1.13

am

1.10

Isn

1.10

dise

1.09

Activations Density 0.032%