INDEX

Explanations

purpose or use

This neuron fires on words that specify allowed-use restrictions and permissions (e.g. “personal,” “non-commercial,” “commercial,” “any,” “purpose”) in license or terms-of-use text.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits



-1.17

thiet

-1.13

 Şubat

-1.13

vaila

-1.13

 Национа

-1.09

pakah

-1.07

惋

-1.06

legung

-1.05

of

-1.04

lessed

-1.04

POSITIVE LOGITS

 purposes

2.61

 tasks

1.86

 purpose

1.77

 Purposes

1.65

 functions

1.53

 activities

1.47

purposes

1.40

用途

1.36

 amaç

1.34

 uses

1.30

Activations Density 0.050%