INDEX

Explanations

determiner + specific noun/verb

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

 disbelief

2.26

 facing

2.17

få

2.10

2.09

नाल्ड

2.04

ن

2.02

ाना

1.94

ﻩ

1.93

decre

1.91

 হঠাৎ

1.91

POSITIVE LOGITS

rid

2.77

ElementsBy

2.63

 додат

2.37

chomp

2.36

aways

2.33

ত্রি

2.32

 angry

2.29

不到

2.26

বয়

2.21

 photons

2.18

Activations Density 0.275%