INDEX

Explanations

nuclear reactor fuel coolant

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_NV

-0.10

mot

-0.10

 Randolph

-0.10

Aub

-0.09

 electr

-0.09

 Moff

-0.09

Air

-0.09

 mold

-0.09

æ¨

-0.09

 stre

-0.09

POSITIVE LOGITS

 neut

0.21

 fuel

0.20

 neutron

0.18

fuel

0.17

 moderator

0.17

 reactor

0.17

 Fuel

0.16

 React

0.16

Fuel

0.16

 graphite

0.15

Activations Density 0.021%