INDEX

Explanations

code comments and structure

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

्स

3.26

еры

3.00

tive

3.00

aa

2.94

yor

2.84

ن

2.78

৩৫

2.76

aan

2.76

tic

2.71

ные

2.64

POSITIVE LOGITS

 subsystems

2.65

その

2.61

 Jeden

2.49

 baff

2.38

("#{

2.36

 espes

2.35

ಾಗಲೇ

2.33

{}",

2.28

面上

2.27

 prolong

2.25

Activations Density 0.000%