INDEX

Explanations

submitting applications

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

ي

2.85

 annet

2.30

 transpiration

2.27

 procedente

2.23

 prud

2.21

outs

2.17

 continuación

2.16

 mycket

2.14

ꔹ

2.10

いない

2.08

POSITIVE LOGITS

stva

2.67

ിയി

2.63

2.58

ם

2.57

HING

2.44

nji

2.33

ই

2.32

 eigenvector

2.28

^{-}$

2.27

 श्रद्धांजलि

2.25

Activations Density 0.104%