INDEX

Explanations

substance abuse and use

np_acts-logits-general · gemini-2.5-flash-lite

The neuron detects mentions of substance use, abuse, and disorders, particularly when discussing addiction or health-related contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The main thing this neuron does is detect mentions of substance use and abuse.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

きる

-1.58

嘮

-1.52

 noin

-1.46

 столько

-1.44

 différences

-1.43

下来的

-1.43

過的

-1.43

-1.41

POSITIVE LOGITS

↵↵

1.86

та

1.72

1.56

besondere

1.54

ющего

1.52

1.50

峩

1.49

 która

1.48

Strange

1.48

 wirklich

1.46

Activations Density 0.018%

substance abuse and use

The neuron detects mentions of substance use, abuse, and disorders, particularly when discussing addiction or health-related contexts.

The main thing this neuron does is detect mentions of substance use and abuse.

No Comments

No Known Activations

substance abuse and use

The neuron detects mentions of substance use, abuse, and disorders, particularly when discussing addiction or health-related contexts.

The main thing this neuron does is detect mentions of substance use and abuse.

No Comments

No Known Activations