INDEX

Circuit Sparsity

No connected neurons data available

Explanations

class attribute assignments (negative activations)

print statement or return value

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

[n

-0.02

(N

-0.02

.name

-0.01

.id

-0.01

(n

-0.01

(num

-0.01

_idx

-0.01

dex

-0.01

_index

-0.01

op

-0.01

POSITIVE LOGITS

plt

0.03

.set

0.01

def

0.01

log

0.01

valid

0.01

ax

0.01

sible

0.01

ab

0.01

 shortest

0.00

Activations Density 90.631%