INDEX

Explanations

specific phrases and titles

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

 mutta

0.27

 কিন্তু

0.26

 δυνατό

0.25

 ша

0.25

 ottimo

0.25

摇

0.25

huh

0.25

 cuda

0.24

 ஆனால்

0.24

 eligible

0.24

POSITIVE LOGITS

ès

0.28

Ia

0.25

adeh

0.24

ínez

0.24

èrent

0.24

<unused512>

0.24

 convincingly

0.24

<unused520>

0.24

<unused711>

0.24

0.23

Activations Density 0.000%