INDEX

Explanations

shocking or shockingly

The neuron selectively activates on occurrences of “shock” and its common morphological variant “shocking.”

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

💼

-2.41

</h3>

-2.08

-2.02

</sub>

-1.91

 signifies

-1.81

蕻

-1.81

.”

-1.79

⭑

-1.77

 emphatically

-1.73

⢅

-1.70

POSITIVE LOGITS

2.39

</b>

2.25

 сказать

1.95

1.81

翼翼

1.78

et

1.76

 Saltar

1.75

 nimmer

1.73

Een

1.70

Ꮠ

1.69

Activations Density 0.011%