INDEX

Explanations

similar to other methods

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

0.61

Massachusetts

0.56

 historic

0.55

ner

0.52

non

0.52

たとえば

0.52

Histor

0.52

0.51

non

0.51

POSITIVE LOGITS

 modalités

1.16

 Bóng

1.12

 mulighed

1.09

ុម

1.08

 possibilité

1.07

 možnost

1.06

 attentes

1.05

 nhưng

1.04

 meningkat

1.04

 variedade

1.04

Activations Density 0.550%