INDEX

Explanations

references to political dysfunction and social issues within government systems

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emiah

-0.07

acier

-0.07

POCH

-0.06

flamm

-0.06

Ð²Ð¸ÑĤ

-0.06

itel

-0.06

iola

-0.06

onaut

-0.06

ifu

-0.06

agar

-0.06

POSITIVE LOGITS

 captive

0.13

 behold

0.12

 controlled

0.12

 dominated

0.11

 captured

0.10

 Capture

0.10

controlled

0.10

 owned

0.09

 subs

0.09

 capture

0.09

Activations Density 0.058%