INDEX

Explanations

months of the year

The neuron detects date-related tokens (months, days, years, and other tokens used in dates).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

리

1.90

ó

1.82

Вы

1.72

Те

1.65

Descripción

1.59

リ

1.58

 compartido

1.56

या

1.55

até

1.55

 протягом

1.55

POSITIVE LOGITS

speople

2.16

 unscathed

1.77

sigh

1.70

landish

1.69

la

1.66

shade

1.66

luft

1.66

いだ

1.66

tion

1.66

deeds

1.61

Activations Density 0.123%