INDEX

Explanations

sick and negative emotions

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

the word "sick" and its variations across different contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

the neuron spotlights occurrences of “sick” (in any form, e.g. sick, sickened, sickest, sick leave).

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

Negative Logits

茑

-2.83

你会

-2.80

阄

-2.66

逦

-2.66

轳

-2.63

鈊

-2.61

–

-2.56

 were

-2.56

秝

-2.53

ネイル

-2.52

POSITIVE LOGITS

2.98

鴬

2.77

的

2.67

»;

2.67

鷙

2.56

 That

2.53

»:

2.52

鯪

2.48

ries

2.47

2.42

Activations Density 0.003%

sick and negative emotions

the word "sick" and its variations across different contexts.

the neuron spotlights occurrences of “sick” (in any form, e.g. sick, sickened, sickest, sick leave).

No Known Activations

sick and negative emotions

the word "sick" and its variations across different contexts.

the neuron spotlights occurrences of “sick” (in any form, e.g. sick, sickened, sickest, sick leave).

No Known Activations