INDEX

Explanations

hit/strike

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hit

-1.77

 struck

-1.51

hit

-1.31

Hit

-1.25

 hits

-1.21

Hit

-1.21

 strike

-1.17

 hitting

-1.11

 striking

-1.04

 strikes

-1.02

POSITIVE LOGITS

rungsseite

0.66

agrid

0.62

beo

0.58

 Biophys

0.57

rinol

0.56

مصادر

0.55

Personensuche

0.54

OGND

0.52

triangleq

0.52

SuspendLayout

0.52

Activations Density 0.028%