INDEX

Explanations

compounding, buffer, cropping

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

و

2.31

емость

2.18

 injustice

2.11

ンの

2.03

тың

1.98

-\

1.93

atre

1.93

брь

1.91

सँग

1.88

inued

1.87

POSITIVE LOGITS

ম

2.87

 arrivé

2.54

 czasie

2.45

how

2.41

hape

2.36

odha

2.27

戯

2.26

NI

2.18

کان

2.17

鹉

2.14

Activations Density 0.000%