INDEX

Explanations

model repository, model ID, model X

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

_models

-0.19

_model

-0.16

 modeling

-0.14

Models

-0.13

 modelling

-0.13

Model

-0.12

 Modeling

-0.12

 models

-0.12

 modeled

-0.11

umba

-0.11

POSITIVE LOGITS

led

0.35

lo

0.19

.addAttribute

0.18

ocked

0.17

ledon

0.17

 Minority

0.15

er

0.15

 minority

0.14

ica

0.13

le

0.13

Activations Density 0.053%