INDEX

Explanations

is to be

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

The neuron consistently activates on the token “to,” i.e. the infinitival/preposition “to.”

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

the “be + to” construction—especially “is to” followed by an infinitive or prepositional phrase indicating intended action, obligation, or position.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

the infinitive marker "to" when used to express purpose, expectation, or obligation in formal or technical writing.

oai_token-act-pair · claude-4-5-sonnet 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

by

-2.23

with

-2.20

-1.98

-1.97

to

-1.95

 одна

-1.92

-1.91

We

-1.89

of

-1.86

-1.84

POSITIVE LOGITS

</h1>

2.27

 alguien

1.96

᠌

1.92

𖥧

1.92

 calientes

1.92

dö

1.89

roslav

1.88

playera

1.87

 “(

1.85

⢧

1.85

Activations Density 0.020%

is to be

The neuron consistently activates on the token “to,” i.e. the infinitival/preposition “to.”

the “be + to” construction—especially “is to” followed by an infinitive or prepositional phrase indicating intended action, obligation, or position.

the infinitive marker "to" when used to express purpose, expectation, or obligation in formal or technical writing.

No Comments

No Known Activations

is to be

The neuron consistently activates on the token “to,” i.e. the infinitival/preposition “to.”

the “be + to” construction—especially “is to” followed by an infinitive or prepositional phrase indicating intended action, obligation, or position.

the infinitive marker "to" when used to express purpose, expectation, or obligation in formal or technical writing.

No Comments

No Known Activations