INDEX

Explanations

then, subsequently, followed by completion

The neuron activates on words that denote cognitive or mental actions or states (e.g. trying, understanding, reading, agreeing).

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

brainly

-1.02

niem

-0.96

 groei

-0.93

 registros

-0.90

віта

-0.89

 zdrav

-0.87

τικού

-0.84

 wirklich

-0.83

sentences

-0.82

seit

-0.82

POSITIVE LOGITS

 then

1.76

Then

1.33

 Then

1.26

然后

1.23

 затем

1.15

 kemudian

1.13

 سپس

1.09

 subsequently

1.05

 ثم

1.04

then

1.03

Activations Density 0.097%