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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Winaray
    -0.55
     viewDidLoad
    -0.50
     propOrder
    -0.48
    Tembelea
    -0.46
    RemindMe
    -0.44
    tiler
    -0.42
     actionBar
    -0.42
    umpang
    -0.42
    mgp
    -0.42
    operatorname
    -0.42
    POSITIVE LOGITS
     new
    0.94
    new
    0.91
     New
    0.87
    New
    0.85
     NEW
    0.81
     Nuevas
    0.76
    NEW
    0.76
     Neue
    0.73
     neuen
    0.73
     Nuevo
    0.69
    Act Density 0.172%

    No Known Activations