INDEX

Explanations

question or asking for help

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

jest

1.54

வே

1.51

bent

1.50

holder

1.39

prin

1.38

 possibilidades

1.38

циям

1.36

於

1.33

){\

1.33

kwargs

1.33

POSITIVE LOGITS

????????

2.34

????

2.09

 diri

1.56

 bombshell

1.55

?.

1.51

.??

1.43

̅

1.42

 stellen

1.42

1.41

 rebuke

1.40

Activations Density 0.111%