INDEX

Explanations

terms related to social judgments and their linguistic expressions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Translated

-0.08

 translation

-0.08

 translated

-0.08

Translation

-0.07

 Translation

-0.07

translation

-0.07

translated

-0.07

 translate

-0.07

 translating

-0.07

Translate

-0.07

POSITIVE LOGITS

 usage

0.10

 Usage

0.09

 Standard

0.09

Usage

0.09

 informal

0.09

USAGE

0.08

usage

0.08

 Inform

0.08

 speakers

0.08

 inform

0.08

Activations Density 0.015%