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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of accents

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of accents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISTORY
    -0.77
    tc
    -0.75
    gone
    -0.75
    tics
    -0.73
    pg
    -0.72
    SOURCE
    -0.70
    tical
    -0.67
    rd
    -0.64
    cible
    -0.64
    PG
    -0.63
    POSITIVE LOGITS
    uated
    1.55
    uates
    1.41
    uate
    1.33
     accent
    1.31
    uating
    1.23
     accents
    1.10
    uation
    1.01
    uations
    0.87
     spoof
    0.76
    inished
    0.74
    Act Density 0.013%

    No Known Activations