INDEX

Explanations

This neuron specifically detects occurrences of the verb “give” (in its various tense and participle forms).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ता

1.16

ST

1.15

EE

1.10

});

1.09

FISH

1.05

STE

1.02

ER

1.01

RA

1.01

이랑

1.01

EAR

1.00

POSITIVE LOGITS

ductory

1.18

 nhiên

1.11

 generously

1.10

یہ

1.04

予

1.02

യും

1.01

 tặng

1.01

 geeft

1.01

 glimpse

0.99

 Gives

0.98

Activations Density 0.061%