INDEX

Circuit Sparsity

No connected neurons data available

Explanations

writing to files or stdout

attribute name 'att' (negative activations)

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

cond

-0.10

split

-0.08

lit

-0.07

raph

-0.07

.edges

-0.07

strip

-0.06

graph

-0.06

POSITIVE LOGITS

random

0.08

.random

0.08

 random

0.08

 Calculate

0.07

))

0.05

abs

0.04

enerate

0.04

ta

0.04

 math

0.04

ri

0.04

Activations Density 100.000%