INDEX

Explanations

good explanation format

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

ä

3.00

ла

2.62

é

2.53

ра

2.35

as

2.29

aucune

2.07

ur

2.06

ästä

2.05

1.99

 lantai

1.93

POSITIVE LOGITS

এর

2.91

ので

2.16

ˏ

2.13

ppt

2.07

̗

2.04

erler

2.02

 polluting

1.99

 பேராசிரியர்

1.96

 sweeping

1.94

 pollute

1.93

Activations Density 0.150%