INDEX

Explanations

stereotype, spec, context, config, resume

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

<bos>

2.69

ინ

2.44

ajikan

2.42

ede

2.40

берриз

2.34

да

2.22

︎

2.22

িল

2.20

ători

2.16

 fruition

2.13

POSITIVE LOGITS

pval

2.91

 wipers

2.81

pickle

2.70

harmonic

2.60

 stereotypes

2.59

pR

2.58

2.56

 ()=>

2.54

 Unwrap

2.54

 cuffs

2.53

Activations Density 0.000%