INDEX

Explanations

chat messages

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

gsSP

-0.88

 refractive

-0.83

 comté

-0.81

瘧

-0.78

Enzyme

-0.77

 motorsport

-0.73

 rallado

-0.72

क्षण

-0.71

ښ

-0.70

 yılında

-0.69

POSITIVE LOGITS

 chat

3.38

 conversation

2.80

 Chat

2.69

chat

2.63

Chat

2.58

 chats

2.58

 messages

2.34

 chatting

2.33

 conversations

2.25

 message

2.17

Activations Density 0.052%