INDEX

Explanations

most/its ... fundamental/basic/core

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

ak

2.87

al

2.80

ر

2.58

er

2.33

 collim

2.31

ils

2.23

 важ

2.15

 образом

2.14

FromNib

2.13

 Mening

2.08

POSITIVE LOGITS

ের

2.61

2.49

ς

2.42

sá

2.33

ﻭ

2.29

هایی

2.28

lessness

2.27

room

2.22

ه

2.17

值

2.16

Activations Density 0.030%