INDEX

Explanations

class and model definition components

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

tensorflow

-0.12

alu

-0.10

=tf

-0.09

 multiplayer

-0.09

avian

-0.08

 initializer

-0.08

 Deadline

-0.08

burgh

-0.08

uster

-0.08

jur

-0.08

POSITIVE LOGITS

 device

0.21

device

0.19

 criterion

0.18

.device

0.16

 loss

0.16

riterion

0.15

Criterion

0.14

 optim

0.14

 Criterion

0.14

 Device

0.14

Activations Density 0.023%