INDEX

Explanations

the neuron fires on blocks of natural-language explanation (prose commentary), as opposed to code tokens.

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

0.41

 which

0.38

 ως

0.38

<sup>

0.36

0.35

 framework

0.34

 versus

0.34

 regions

0.34

 மற்றும்

0.34

POSITIVE LOGITS

 Paise

0.42

Não

0.41

Tidak

0.40

 দেরী

0.40

nicht

0.39

誑

0.39

တတ်

0.38

VerFile

0.38

 Probleme

0.38

tidak

0.38

Activations Density 0.000%