INDEX

Explanations

The neuron chiefly activates on numeric tokens—especially floating‐point or multi-digit numbers.

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

head content words—especially nouns or named entities functioning as the core of a phrase within a sentence.

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

the word "Any" appearing at the beginning of a sentence or clause in formal, legal, or technical documents.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_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

 более

0.85

ை

0.81

бычно

0.79

ровкой

0.79

 população

0.78

 руководство

0.78

ా

0.78

 соотно

0.77

iteľ

0.76

hältnis

0.76

POSITIVE LOGITS

єю

0.84

ନ୍ଦ

0.84

 breeze

0.82

 concerts

0.80

 professions

0.79

 restaurants

0.79

qRT

0.78

 sandals

0.77

OLOGIE

0.77

 bouquet

0.75

Activations Density 0.000%

The neuron chiefly activates on numeric tokens—especially floating‐point or multi-digit numbers.

head content words—especially nouns or named entities functioning as the core of a phrase within a sentence.

the word "Any" appearing at the beginning of a sentence or clause in formal, legal, or technical documents.

No Comments

No Known Activations

The neuron chiefly activates on numeric tokens—especially floating‐point or multi-digit numbers.

head content words—especially nouns or named entities functioning as the core of a phrase within a sentence.

the word "Any" appearing at the beginning of a sentence or clause in formal, legal, or technical documents.

No Comments

No Known Activations