INDEX

Explanations

describing fatty or large things

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

the word "fat" and related forms, often when describing size or used in names/phrases.

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

This neuron fires on occurrences of the standalone token “Fat.”

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

鹚

-2.33

〤

-2.30

;"

-2.25

 umožňuje

-2.20

和她

-2.20

人才

-2.20



-2.17

 シルエット

-2.16

.'

-2.13

匆

-2.13

POSITIVE LOGITS

It

2.52

 When

2.42

Its

2.30

 Когда

2.13

2.11

your

1.97

此时

1.91

you

1.91

To

1.88

现在的

1.87

Activations Density 0.010%

describing fatty or large things

the word "fat" and related forms, often when describing size or used in names/phrases.

This neuron fires on occurrences of the standalone token “Fat.”

No Comments

No Known Activations

describing fatty or large things

the word "fat" and related forms, often when describing size or used in names/phrases.

This neuron fires on occurrences of the standalone token “Fat.”

No Comments

No Known Activations