INDEX

Explanations

`a` followed by `story` or `ten`

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

ldots

1.24

okas

1.23

িয়ন

1.18

เอียด

1.16

ي

1.13

umoto

1.11

ки

1.10

י

1.10

se

1.09

POSITIVE LOGITS

ें

1.31

ів

1.30

 tortue

1.21

 étudiant

1.21

 ľud

1.20

 produc

1.18

 Aufgabe

1.17

 effetto

1.17

intérêt

1.16

 phú

1.16

Activations Density 0.004%