INDEX

Explanations

explaining and emphasizing

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

Which

1.15

 Which

1.11

 която

0.98

 които

0.94

 které

0.93

which

0.93

 기준으로

0.92

которые

0.92

 ktoré

0.89

 která

0.89

POSITIVE LOGITS

 profound

1.26

 hypocrisy

1.16

 stark

1.16

why

1.15

 inherent

1.12

how

1.12

 humility

1.11

 uncomfortable

1.07

 powerfully

1.07

 vividly

1.05

Activations Density 0.355%