INDEX

Explanations

might followed by verbs

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

 contains

0.24

 Contains

0.22

 decomposition

0.20

Contains

0.20

 itself

0.20

 distribution

0.19

 functions

0.19

contains

0.19

 permeates

0.18

 inhibitory

0.18

POSITIVE LOGITS

 want

0.27

记得

0.24

 expect

0.23

 choose

0.23

 forgo

0.23

 realize

0.22

 WANT

0.22

 chose

0.22

use

0.21

 decide

0.20

Activations Density 0.044%