INDEX

Explanations

mentions of political figures, specifically Narendra Modi and Amit Shah

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

occo

-0.07

ipt

-0.07

nett

-0.07

erves

-0.07

 Hispan

-0.06

lectic

-0.06

onical

-0.06

Ã³m

-0.06

.metro

-0.06

.files

-0.06

POSITIVE LOGITS

 mitt

0.07

OV

0.06

isti

0.06

 Mell

0.06

Pa

0.06

HCI

0.06

jer

0.06

 Hind

0.06

#ad

0.06

angl

0.06

Activations Density 0.002%