INDEX

Explanations

attributing statements to speakers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Those

-1.47

IZZA

-1.39

 таких

-1.37

再来

-1.36

 těchto

-1.35

 verrou

-1.34

"))

-1.34

現貨

-1.33

Kunden

-1.33

")

-1.31

POSITIVE LOGITS

our

1.82

 хотел

1.59

 открыть

1.58

旁边的

1.56

一旁的

1.52

 WHICH

1.52

’

1.48

背后的

1.46

the

1.45

 possono

1.44

Activations Density 0.015%