INDEX

Explanations

a predictioninference process

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

DataSet

-0.10

 trainable

-0.09

 Poverty

-0.08

.learning

-0.08

 Learning

-0.08

 chap

-0.08

Regressor

-0.08

 liken

-0.08

 Reyn

-0.08

shuffle

-0.08

POSITIVE LOGITS

 inference

0.21

 infer

0.17

 forward

0.17

infer

0.14

ference

0.14

forward

0.13

 Forward

0.13

 Infer

0.13

 model

0.12

Forward

0.11

Activations Density 0.123%