INDEX

Explanations

repeated vowels or letters

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

nement

1.24

ación

1.20

nél

1.09

४

1.09

ución

1.09

ión

1.05

ных

1.04

्टी

1.04

५

1.03

ih

1.00

POSITIVE LOGITS

for

1.42

1.30

ני

1.28

 sicuro

1.24

те

1.23

യ

1.21

inį

1.20

на

1.20

 rimane

1.19

 impegno

1.19

Activations Density 0.002%