Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quiao
    -0.70
    AISSEE
    -0.64
    Хьажоргаш
    -0.62
    }{*}{}
    -0.62
    脚注の使い方
    -0.62
     cabrio
    -0.61
    primaryStage
    -0.60
    DockStyle
    -0.60
    CodedInputStream
    -0.60
    Foxy
    -0.58
    POSITIVE LOGITS
    enumi
    0.59
     taas
    0.58
    HasAnnotation
    0.57
    seamnă
    0.56
     new
    0.54
     CreateTagHelper
    0.50
    ̈́
    0.50
     montagna
    0.50
     autorytatywna
    0.49
    __(/*!
    0.49
    Act Density 0.006%

    No Known Activations