INDEX

Explanations

function arguments and return values

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 kill

0.80

now

0.77

 enemy

0.74

 proclaiming

0.73

 become

0.72

 became

0.72

 proved

0.72

<start_of_image>

0.71

inn

0.70

 slain

0.70

POSITIVE LOGITS

Args

1.89

Returns

1.86

 Args

1.66

 Returns

1.55

returns

1.44

Parameters

1.36

Arguments

1.33

"""

1.31

 returns

1.26

 RETURNS

1.24

Activations Density 0.483%

No Known Activations