INDEX

Explanations

references to addiction and desensitization

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

ataka

-0.07

Ð°Ð»Ñĭ

-0.07

Î¼ÏĢ

-0.07

eldorf

-0.07

onte

-0.07

 vmax

-0.06

èĲ½

-0.06

hiba

-0.06

ej

-0.06

arella

-0.06

POSITIVE LOGITS

 habit

0.10

 Ð¿ÑĢÐ¸Ð²Ñĭ

0.10

Hab

0.10

 Habit

0.10

habit

0.09

 Adapt

0.09

hab

0.09

hab

0.09

ä¹ł

0.09

adapt

0.09

Activations Density 0.044%