INDEX

Explanations

something warrants attention

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

ి

1.44

ﻧ

1.43

岖

1.41

์

1.39

vì

1.33

ремя

1.32

ه

1.30

mente

1.30

 mình

1.30

слов

1.27

POSITIVE LOGITS

 Tinggi

1.74

lard

1.64

ज

1.64

larda

1.57

লিত

1.55

जवळ

1.54

asını

1.52

어

1.50

lz

1.43

lika

1.42

Activations Density 0.023%