INDEX

Explanations

concession or contrast

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DebugSymbols

2.81

ност

2.77

teki

2.73

sto

2.64

𝘭

2.63

ന്ത്രാ

2.60

 гори

2.59

vak

2.56

nlü

2.51

 poni

2.45

POSITIVE LOGITS

{@

2.77

మం

2.66

แหน

2.46

пря

2.26

iteks

2.25

的

2.25

̡

2.24

 Doch

2.24

==============]

2.23

 Booster

2.19

Activations Density 0.009%