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

    Neuronpedia

    INDEX
    Explanations

    references to individuals who identify as beginners in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ontale
    -0.59
    lanniksi
    -0.54
     chì
    -0.52
    rzez
    -0.52
     lunches
    -0.51
    erobe
    -0.51
    那就是
    -0.50
    ligently
    -0.50
    avits
    -0.49
    Скачать
    -0.49
    POSITIVE LOGITS
     novice
    0.84
     unfamiliar
    0.84
     beginner
    0.80
     newcomer
    0.79
     Anfänger
    0.78
     newcomers
    0.78
     beginners
    0.74
    Beginner
    0.73
     Novice
    0.73
     newbies
    0.73
    Act Density 0.182%

    No Known Activations