INDEX

Explanations

speech contexts

hate speech and freedom of speech

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 মর

0.43

∗</

0.43

擰

0.42

鲳

0.41

धिका

0.41

⦖

0.38

ல்ல

0.38

 saisons

0.38

ობა

0.38

 обсу

0.37

POSITIVE LOGITS

 speech

4.47

speech

4.16

 Speech

4.13

Speech

4.06

 speeches

3.50

 भाषण

3.05

 речи

2.59

 स्पी

2.55

SPE

2.20

演讲

2.20

Activations Density 0.070%