INDEX

Explanations

theories

The neuron specifically activates on occurrences of the word “theory” or its plural “theories.”

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

नलोड

-2.33

 فقط

-2.13

前言

-1.96

齜

-1.95

躂

-1.88



-1.87

 citoy

-1.81

ching

-1.81

用法

-1.79

的很

-1.72

POSITIVE LOGITS

2.83

 that

2.11

 Schluß

2.09

of

2.05

 vorigen

1.91

re

1.88

 geringen

1.84

 garantiert

1.83

 verschied

1.82

 Durchsch

1.82

Activations Density 0.014%