INDEX

Explanations

arrow and pointer

The neuron activates on occurrences of the word “arrow” (including its plural “arrows”).

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

僅

-1.57

Putting

-1.50

я

-1.49

 odası

-1.48

-1.45

🏗

-1.45

-1.44

.'”

-1.36

Identifying

-1.35

rítica

-1.34

POSITIVE LOGITS

を使用

1.87

 ส์

1.84

隳

1.81

鼍

1.79



1.72

 vicente

1.69

 presentó

1.68

IALES

1.67

are

1.66

➷

1.63

Activations Density 0.030%