INDEX

Explanations

(re)linking words, (sub)luxation, chemicals, Research, Franklin

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

prefixes in parentheses such as "(un)", "(re)", and "(sub)" that modify words.

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

The neuron fires on bound morphemes—common prefixes, suffixes, and stem fragments (e.g. “re‐,” “sub‐,” “un‐,” “‐ation”) within longer, often technical or compound words.

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

-1.93

-1.55

//

-1.45

檍

-1.42

-1.40

 behauptet

-1.38

JsonPropertyName

-1.37

-1.36

POSITIVE LOGITS

近年来

1.48

ampaikan

1.46

鹟

1.45

镂

1.45

雳

1.45

ప్ర

1.44

конструк

1.41

 ďal

1.41

Կ

1.41

 olej

1.40

Activations Density 0.093%

(re)linking words, (sub)luxation, chemicals, Research, Franklin

prefixes in parentheses such as "(un)", "(re)", and "(sub)" that modify words.

The neuron fires on bound morphemes—common prefixes, suffixes, and stem fragments (e.g. “re‐,” “sub‐,” “un‐,” “‐ation”) within longer, often technical or compound words.

No Comments

No Known Activations

(re)linking words, (sub)luxation, chemicals, Research, Franklin

prefixes in parentheses such as "(un)", "(re)", and "(sub)" that modify words.

The neuron fires on bound morphemes—common prefixes, suffixes, and stem fragments (e.g. “re‐,” “sub‐,” “un‐,” “‐ation”) within longer, often technical or compound words.

No Comments

No Known Activations