INDEX

Explanations

ongoing or future actions

tokens that indicate continuation or ongoing/continuous action (words signaling something continues).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.79

’

1.55

1.38

،

1.22

1.17

、

1.17

).

1.08

ı

1.08

\"

1.05

1.04

POSITIVE LOGITS

the

1.98

تي

1.60

1.48

на

1.48

1.41

توان

1.35

ر

1.34

is

1.33

1.25

to

1.24

Activations Density 0.087%