INDEX

Explanations

in vivo or in vitro

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

punctuation at the end of sentences, particularly periods.

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

The neuron responds most strongly to common grammatical function words—especially “are” and “in” (and similar link verbs/prepositions).

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

 instead

-1.65

不断的

-1.25

 tril

-1.18

 スタンダード

-1.17

 again

-1.16

牆

-1.14

 also

-1.13

鼕

-1.12

 brevet

-1.10

ずる

-1.10

POSITIVE LOGITS

1.51

was

1.35

 sowie

1.34

1.33

1.31

かなり

1.29

"'

1.28

 barvy

1.24

".

1.23

 beeinf

1.23

Activations Density 0.131%

in vivo or in vitro

punctuation at the end of sentences, particularly periods.

The neuron responds most strongly to common grammatical function words—especially “are” and “in” (and similar link verbs/prepositions).

No Comments

No Known Activations

in vivo or in vitro

punctuation at the end of sentences, particularly periods.

The neuron responds most strongly to common grammatical function words—especially “are” and “in” (and similar link verbs/prepositions).

No Comments

No Known Activations