zero before a decimal point

What this neuron does

This neuron fires on the zero in numbers that start with a decimal, like '0.71' or '0.805'. It mostly reacts to the zero before the dot, and turning it up made the model repeat short words like 'I' and 'The' over and over, which does not clearly relate to numbers.

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

   to directly correlate the LLCCs length to the diameter of the inner tubes and determine the optimal diameter for the high yield growth of carbyne (about 0.71 nm). Our approach of HV high temperature annealing has a great

2. #2 peak

   generating the stress field. Layers dips by 20-degree increments, with differing elastic moduli, represented by stiffness ratios (EU/EL) ranging from 0.01 to 100. Our findings validate prior research on heterogeneous

3. #3 peak

   people testing highly positive for the peanut antibodies, tiny proteins made by the body when exposed to the allergens. About 1 percent were allergic to shrimp, 0.4 percent were allergic to eggs and 0.2 percent were allergic to

4. #4 peak

   where c = (10/9)2 ≈ 1.2 and x = (9/10)log102 ≈ 0.97. The expected number of powers of 2 without zeroes starting from

5. #5 peak

   , at least near the surface, over the entire region. The methods being developed use airborne hyperspectral and multi-spectral high-resolution imagery and very high resolution (0.<|endoftext|>Components of population growth⏎Information identified as archived is provided for reference,

6. #6 peak

   CI = 1.618-2.398), while fewer manifested fever (p = 0.046, OR = 0.758, 95% CI = 0.57

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

   10⏎Disruption of the right temporoparietal junction with transcranial magnetic stimulation reduces the role of beliefs in moral judgments⏎A great article in PNAS:<|endoftext|>In this chapter we present a model for the design of a conversation

2. #2 peak

   cells; that it wreaks havoc on the bodies of patients is unsurprising. But chemo may also affect their unborn children. According to a new study in PNAS, the offspring of mice treated with chemotherapy have higher rates of mutation, even

3. #3 peak

   ma said. “That’s the potential of this technology.”⏎Results from the initial ICU study were published Thursday in the medical journal PLOS ONE. The OSU researchers have applied for FDA emergency use authorization and hope

4. #4 peak

   2 students learn to tell and write time from analog and digital clocks to the nearest five minutes, using a.m. and p.m.⏎Common Core: 2.MD.7⏎

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.