gap before a year in citations

What this neuron does

This neuron fires on the blank spot just before the year in author-date citations such as "(Castaneda 1998)" or "(Courneya, Estabrooks & Nigg 1997)". Turning it up or down did not change the text in a way that relates to citations.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   where_x, float where_y, float where_z);⏎void deallocate_model(model_3d_ref kill_this);⏎The compiler doesn't read your code like this

2. #2 peak

   eligible for the National Register of Historic Places.⏎The state of Wyoming did not concur and recommended further work before a⏎determination was made (Stephanson 1992).

3. #3 peak

   by the tour operator. It ensures safeguards and security of passengers and their luggages and provides remedies against damages to passengers (Van Hoof and Pennings, 2018).⏎Air Transport Law: Air transport law legislation aims safety of

4. #4 peak

   exercise program tend to be the individuals who fail to realize their exercise intentions…⏎(Marcus, Forsyth, Stone, Dubbert, McKenzie, Dunn & Blair 2000) This lack of physical activity among the elderly is of even

5. #5 peak

   ⏎f :: Bool -> [Int]⏎f b = if b then xs else ⏎-- With library⏎g :: Bool -> [Int]⏎g = mwhen xs⏎See? It’s an amazing 14 characters shorter!⏎The current version

6. #6 peak

   intention has generally been insignificant among older and younger adults. (Courneya, Estabrooks & Nigg 1997) Unlike attitude, which tends to consistently account for approximately

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

1. #1 peak

   disappear when solutions are available for black holes embedded in arbitrary backgrounds.⏎|Original language||English (US)|⏎|Number of pages||12|⏎|Journal||Classical and Quantum Gravity|⏎|State||Published - Jul 7 2

2. #2 peak

   access all content.<|endoftext|>Great Slaty becomes World's Largest Woodpecker as Ivory Billed Goes Extinct⏎22 November 2021 | Vibhav peri | Crises⏎The Great Slaty Woodpecker

3. #3 peak

   of Text Reinterpretation Skill.⏎Bonitatibus, Gary; Beal, Carole R.⏎Four studies investigated when children became able to detect that the words

4. #4 peak

   active components of DST can be replicated in other school environments.⏎Source: Health Behavior and Policy Review, Volume 8, Number 4, July 2021, pp. 281

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.