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

    Neuronpedia

    INDEX
    Explanations

    terms related to turbocharging engines and inflation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Turbo" and related terms indicating speed or boost

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lyon
    -0.81
     Ell
    -0.73
     Griffith
    -0.71
    IFF
    -0.71
     McGill
    -0.70
     Luk
    -0.69
     Picks
    -0.68
     Nurs
    -0.68
     Cull
    -0.68
     Nem
    -0.67
    POSITIVE LOGITS
     Turbo
    2.69
     turbo
    2.43
    Tur
    2.06
    tur
    1.99
     infl
    1.81
     fueled
    1.56
     fueling
    1.48
     fuelled
    1.36
     turb
    1.33
     refuel
    1.26
    Act Density 0.047%

    No Known Activations