INDEX

Explanations

No Explanations Found

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

ele

1.40

ead

1.38

eal

1.30

alu

1.22

iendo

1.21

escent

1.19

<bos>

1.18

elem

1.17

iertas

1.15

eer

1.13

POSITIVE LOGITS

 convulsions

1.29

 apical

1.24

감이

1.21

 Sasaki

1.18

䔀

1.18



1.17

 Confederate

1.16

 iteration

1.13

 Confederacy

1.11

ફળ

1.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.