INDEX

Explanations

positive or negative

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

 аса

-0.84

 bender

-0.82

seteq

-0.82

 Tisch

-0.77

)<\

-0.77

 sels

-0.75

 Île

-0.72

реи

-0.72

 財布

-0.70

 تاب

-0.69

POSITIVE LOGITS

 negative

6.09

 positive

5.16

negative

5.09

 Negative

4.84

Negative

4.69

positive

4.34

NEGATIVE

4.03

Positive

3.94

 Positive

3.94

 NEGATIVE

3.89

Activations Density 0.096%