INDEX

Explanations

conjunctions and specific entities

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Though

1.23

雖

1.10

Although

1.10

Even

1.10

even

1.09

虽然

1.06

Aunque

1.06

虽

1.06

though

1.03

 Though

1.01

POSITIVE LOGITS

 ultimately

1.50

 nonetheless

1.37

 overall

1.28

 nevertheless

1.25

 fundamentally

1.11

 undeniably

1.11

 Ultimately

1.10

 일반적으로

1.01

 concurrently

1.01

 enabling

1.01

Activations Density 0.015%