INDEX

Explanations

references to groups or multiple items—plural, category-like mentions and set-introducing determiners that signal lists or collections in expository text.

oai_token-act-pair · gpt-5 Triggered by @smilgaveronika

plural nouns

np_max-act · gpt-5 Triggered by @smilgaveronika

are

np_max-act-logits · gpt-5 Triggered by @smilgaveronika

New Auto-Interp

Configuration

google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ತನ್ನ

1.27

 தனது

1.23

まさ

1.17

 היה

1.16

 தன்

1.12

కుంది

1.09

 заявил

1.06

 понял

1.06

 మారింది

1.06

因为它

1.05

POSITIVE LOGITS

are

4.05

 aren

3.33

 đều

3.33

 são

3.22

 were

3.14

都是

3.05

都很

3.03

都可以

2.97

 jsou

2.95

 sono

2.95

Activations Density 4.748%

references to groups or multiple items—plural, category-like mentions and set-introducing determiners that signal lists or collections in expository text.

plural nouns

are

No Comments

No Known Activations

references to groups or multiple items—plural, category-like mentions and set-introducing determiners that signal lists or collections in expository text.

plural nouns

are

No Comments

No Known Activations