INDEX

Explanations

pay attention

The neuron fires on main action verbs—lexical verbs (e.g. played, show, assigned, providing) that denote the primary events or activities in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 pliers

1.04

 catastrophes

1.03

 vulgaris

1.00

worthiness

0.99

 disasters

0.98

 incomes

0.97

lands

0.95

ﻄ

0.95

 cucumbers

0.94

ov

0.94

POSITIVE LOGITS

廻

0.99

 credence

0.97

على

0.94

↵

0.93

 রেখে

0.91

Flower

0.89

хову

0.89

 название

0.88

ه

0.88

Snapshot

0.87

Activations Density 1.123%