INDEX

Explanations

code structure keywords

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

tive

3.30

tions

3.19

जूद

2.68

 aloud

2.64

০

2.61

tion

2.56

plaintext

2.52

 dissociate

2.51

2.46

 DISCLAIMED

2.45

POSITIVE LOGITS

ever

2.63

ך

2.55

er

2.44

ہیں

2.36

eg

2.27

ە

2.24

帼

2.23

ชา

2.23

sib

2.21

matig

2.20

Activations Density 0.047%