INDEX

Explanations

magnitude

The neuron detects numeric measurement tokens (e.g. numerical values and magnitudes, including decimals).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 revolved

-2.44

不是

-2.17

 включая

-1.96

 What

-1.91

 regimen

-1.89

🫠

-1.85

 Instead

-1.84

 しま

-1.83

 misled

-1.83



-1.82

POSITIVE LOGITS

of

2.94

量

2.00

</sup>

1.98

𓍊

1.91

1.89

姽

1.75

 και

1.74

 ваши

1.73

și

1.70

Activations Density 0.017%