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

    Neuronpedia

    INDEX
    Explanations

    mentions of different accents and descriptions of how they sound

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different types of accents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =================================
    -0.72
    tc
    -0.71
    Internal
    -0.71
     Abandon
    -0.67
    Trend
    -0.66
     Skydragon
    -0.65
    tical
    -0.65
    advertising
    -0.64
    Tri
    -0.64
    pg
    -0.63
    POSITIVE LOGITS
    uated
    1.54
    uates
    1.40
    uate
    1.38
    uating
    1.27
     accent
    1.11
    uation
    1.07
     accents
    0.99
     poppy
    0.90
    uations
    0.87
     pronunciation
    0.73
    Act Density 0.029%

    No Known Activations